{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:51:42Z","timestamp":1775065902111,"version":"3.50.1"},"reference-count":458,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Natural Sciences and Engineering Research Council (NSERC) Discovery Program"},{"name":"NSERC CREATE TRAVERSAL Program"},{"name":"Innovation for Defence Excellence and Security (IDEaS) Program from the Department of National Defence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Commun. Soc."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/ojcoms.2024.3456549","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T18:06:17Z","timestamp":1725905177000},"page":"5799-5856","source":"Crossref","is-referenced-by-count":114,"title":["LLM-Based Edge Intelligence: A Comprehensive Survey on Architectures, Applications, Security and Trustworthiness"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1160-2846","authenticated-orcid":false,"given":"Othmane","family":"Friha","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0632-3172","authenticated-orcid":false,"given":"Mohamed","family":"Amine Ferrag","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Digital Science Research Center, Technology Innovation Institute, Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0220-7956","authenticated-orcid":false,"given":"Burak","family":"Kantarci","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"}]},{"given":"Burak","family":"Cakmak","sequence":"additional","affiliation":[{"name":"Headquarters, Edge Signal, Ottawa, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5508-9733","authenticated-orcid":false,"given":"Arda","family":"Ozgun","sequence":"additional","affiliation":[{"name":"Headquarters, Edge Signal, Ottawa, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5271-5970","authenticated-orcid":false,"given":"Nassira","family":"Ghoualmi-Zine","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Badji Mokhtar-Annaba University, Annaba, Algeria"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The Language Instinct: How the Mind Creates Language","author":"Pinker","year":"2003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-6710-5_3"},{"key":"ref3","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"ref5","volume-title":"Statistical Methods for Speech Recognition","author":"Jelinek","year":"1998"},{"key":"ref6","first-page":"1","article-title":"A neural probabilistic language model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"13","author":"Bengio"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2021.114135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"ref11","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref12","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref13","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref14","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv:2206.07682"},{"key":"ref15","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref18","article-title":"Confidant: Customizing transformer-based LLMs via collaborative edge training","author":"Chen","year":"2023","journal-title":"arXiv:2311.13381"},{"key":"ref19","article-title":"TrustLLM: Trustworthiness in large language models","author":"Sun","year":"2024","journal-title":"arXiv:2401.05561"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref21","volume-title":"Artificial intelligence act","author":"Parliament","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref23","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref24","article-title":"AWQ: Activation-aware weight quantization for LLM compression and acceleration","author":"Lin","year":"2023","journal-title":"arXiv:2306.00978"},{"key":"ref25","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref26","article-title":"BitNet: Scaling 1-bit transformers for large language models","author":"Wang","year":"2023","journal-title":"arXiv:2310.11453"},{"key":"ref27","article-title":"BiLLM: Pushing the limit of post-training quantization for LLMs","author":"Huang","year":"2024","journal-title":"arXiv:2402.04291"},{"key":"ref28","article-title":"Extreme compression of large language models via additive quantization","author":"Egiazarian","year":"2024","journal-title":"arXiv:2401.06118"},{"key":"ref29","article-title":"Efficient LLM inference on CPUS","author":"Shen","year":"2023","journal-title":"arXiv:2311.00502"},{"key":"ref30","volume-title":"Deploy large language models at the edge with NVIDIA IGX Orin developer kit","author":"Nelson","year":"2023"},{"key":"ref31","volume-title":"Accelerating generative AI at the edge","author":"Soriaga","year":"2023"},{"key":"ref32","article-title":"The era of 1-bit LLMs: All large language models are in 1.58 bits","author":"Ma","year":"2024","journal-title":"arXiv:2402.17764"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2023.10272352"},{"key":"ref34","article-title":"EdgeMoE: Fast on-device inference of MoE-based large language models","author":"Yi","year":"2023","journal-title":"arXiv:2308.14352"},{"key":"ref35","article-title":"LAMBO: Large language model empowered edge intelligence","author":"Dong","year":"2023","journal-title":"arXiv:2308.15078"},{"key":"ref36","article-title":"Federated fine-tuning of LLMS on the very edge: The good, the bad, the ugly","author":"Woisetschl\u00e4ger","year":"2023","journal-title":"arXiv:2310.03150"},{"key":"ref37","article-title":"Identifying and mitigating vulnerabilities in LLM-integrated applications","author":"Jiang","year":"2023","journal-title":"arXiv:2311.16153"},{"key":"ref38","first-page":"20852","article-title":"Less is more: Task-aware layer-wise distillation for language model compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref39","article-title":"FATE-LLM: A industrial grade federated learning framework for large language models","author":"Fan","year":"2023","journal-title":"arXiv:2310.10049"},{"key":"ref40","article-title":"MemGPT: Towards LLMS as operating systems","author":"Packer","year":"2023","journal-title":"arXiv:2310.08560"},{"key":"ref41","article-title":"A simple and effective pruning approach for large language models","author":"Sun","year":"2023","journal-title":"arXiv:2306.11695"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2947490"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2970550"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3119950"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3135829"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126076"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2000318"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3189962"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3353265"},{"key":"ref52","article-title":"A survey of resource-efficient LLM and multimodal foundation models","author":"Xu","year":"2024","journal-title":"arXiv:2401.08092"},{"key":"ref53","article-title":"Security and privacy challenges of large language models: A survey","author":"Das","year":"2024","journal-title":"arXiv:2402.00888"},{"key":"ref54","article-title":"Large language models: A survey","author":"Minaee","year":"2024","journal-title":"arXiv:2402.06196"},{"key":"ref55","article-title":"Pushing large language models to the 6G edge: Vision, challenges, and opportunities","author":"Lin","year":"2023","journal-title":"arXiv:2309.16739"},{"key":"ref56","article-title":"Enabling AI-generated content (AIGC) services in wireless edge networks","author":"Du","year":"2023","journal-title":"arXiv:2301.03220"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2941458"},{"key":"ref60","article-title":"6G white paper on edge intelligence","author":"Peltonen","year":"2020","journal-title":"arXiv:2004.14850"},{"key":"ref61","first-page":"1","article-title":"EdgeAI: A vision for distributed, edge-native artificial intelligence in future 6G networks","volume-title":"Proc. 6G Wireless Summit","author":"Lov\u00e9n"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2915983"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3251297"},{"key":"ref64","article-title":"Defining AI native: A key enabler for advanced intelligent telecom networks","year":"2024"},{"key":"ref65","volume-title":"Toward a 6G AI-native air interface","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118346"},{"key":"ref67","article-title":"How can AI be distributed in the computing continuum? Introducing the neural pub\/sub paradigm","author":"Lov\u00e9n","year":"2023","journal-title":"arXiv:2309.02058"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ITIA50152.2020.9312286"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3244674"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.2000735"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/EuCNC\/6GSummit51104.2021.9482503"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/mcom.001.2300550"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.02.004"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/s20092533"},{"key":"ref76","volume-title":"EdgeTPU","year":"2024"},{"key":"ref77","volume-title":"Explore whats next in embedded computing","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00104"},{"key":"ref79","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref80","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv:2404.14219","author":"Abdin","year":"2024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13050826"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22170-5_10"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2024.3349956"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.24"},{"key":"ref85","volume-title":"Differences between MTBF and MTTR","year":"2024"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15592-7"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103097"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3363469"},{"key":"ref89","article-title":"Beyond efficiency: A systematic survey of resource-efficient large language models","author":"Bai","year":"2024","journal-title":"arXiv:2401.00625"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref91","volume-title":"Introducing apples on-device and server foundation models","year":"2024"},{"key":"ref92","article-title":"6G networks: Beyond Shannon towards semantic and goal-oriented communications","volume":"190","author":"Strinati","year":"2021","journal-title":"Comput. Netw."},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2001239"},{"key":"ref94","article-title":"Towards semantic communication protocols for 6g: From protocol learning to language-oriented approaches","author":"Park","year":"2023","journal-title":"arXiv:2310.09506"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.101.2100269"},{"key":"ref96","article-title":"Large AI model empowered multimodal semantic communications","author":"Jiang","year":"2023","journal-title":"arXiv:2309.01249"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600940"},{"key":"ref98","article-title":"LLM processes: Numerical predictive distributions conditioned on natural language","author":"Requeima","year":"2024","journal-title":"arXiv:2405.12856"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00632"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.03.003"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2984887"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-019-0355-6"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.001.2000054"},{"key":"ref104","article-title":"Terahertz communications (TeraCom): Challenges and impact on 6G wireless systems","author":"Han","year":"2019","journal-title":"arXiv:1912.06040"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2921522"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.005.2400019"},{"key":"ref107","article-title":"Leveraging large language models for integrated satellite-aerial-terrestrial networks: Recent advances and future directions","author":"Javaid","year":"2024","journal-title":"arXiv:2407.04581"},{"key":"ref108","article-title":"An overview of machine learning-enabled optimization for reconfigurable intelligent surfaces-aided 6G networks: From reinforcement learning to large language models","author":"Zhou","year":"2024","journal-title":"arXiv:2405.17439"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3384013"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2024.3395748"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3249835"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/6GSUMMIT49458.2020.9083794"},{"key":"ref113","article-title":"White paper on critical and massive machine type communication towards 6G","author":"Mahmood","year":"2020","journal-title":"arXiv:2004.14146"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-021-02010-5"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2921208"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900287"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003925"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2100164"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/3603287.3651205"},{"key":"ref120","article-title":"FusionAI: Decentralized training and deploying LLMs with massive consumer-level GPUs","author":"Tang","year":"2023","journal-title":"arXiv:2309.01172"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524340"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.014.2300319"},{"key":"ref123","article-title":"Towards building the federated GPT: Federated instruction tuning","author":"Zhang","year":"2023","journal-title":"arXiv:2305.05644"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3510033"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671582"},{"key":"ref126","article-title":"Adaptive layer splitting for wireless LLM inference in edge computing: A model-based reinforcement learning approach","author":"Chen","year":"2024","journal-title":"arXiv:2406.02616"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10570793"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656592"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3402237"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.2024.3420120"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3413047"},{"key":"ref132","article-title":"Large language models in 6G security: Challenges and opportunities","author":"Nguyen","year":"2024","journal-title":"arXiv:2403.12239"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/EuCNC\/6GSummit51104.2021.9482609"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3362271"},{"key":"ref135","article-title":"Dynamic and adaptive feature generation with LLM","author":"Zhang","year":"2024","journal-title":"arXiv:2406.03505"},{"key":"ref136","article-title":"6GSoft: Software for edge-to-cloud continuum","author":"Akbar","year":"2024","journal-title":"arXiv:2407.05963"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/6GSUMMIT49458.2020.9083832"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/6GSUMMIT49458.2020.9083784"},{"key":"ref139","article-title":"Federated TrustChain: Blockchain-enhanced LLM training and unlearning","author":"Zuo","year":"2024","journal-title":"arXiv:2406.04076"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ACDSA59508.2024.10467706"},{"key":"ref141","article-title":"SecureFalcon: The next cyber reasoning system for cyber security","author":"Ferrag","year":"2023","journal-title":"arXiv:2307.06616"},{"key":"ref142","article-title":"NetGPT: A native-AI network architecture beyond provisioning personalized generative services","author":"Chen","year":"2023","journal-title":"arXiv:2307.06148"},{"key":"ref143","article-title":"PrivateLoRA for efficient privacy preserving LLM","author":"Wang","year":"2023","journal-title":"arXiv:2311.14030"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.13052\/jwe1540-9589.2263"},{"key":"ref145","article-title":"Towards integrated fine-tuning and inference when generative AI meets edge intelligence","author":"Chen","year":"2024","journal-title":"arXiv:2401.02668"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3009876"},{"key":"ref147","volume-title":"ChatGPT account takeover\u2014Wildcard Web cache deception","year":"2024"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/3486221"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1002\/9781119501121.ch2"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.07.033"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2017.1700271"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/EDGE.2019.00028"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/LANMAN.2018.8475113"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13112077"},{"key":"ref155","article-title":"PerLLM: Personalized inference scheduling with edge-cloud collaboration for diverse LLM services","author":"Yang","year":"2024","journal-title":"arXiv:2405.14636"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2023-Fall60731.2023.10333824"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/FMEC.2018.8364046"},{"key":"ref158","article-title":"User association and resource allocation in large language model based mobile edge computing system over wireless communications","author":"Qian","year":"2023","journal-title":"arXiv:2310.17872"},{"key":"ref159","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref160","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Stat.","author":"McMahan"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3315066"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ACSOS-C58168.2023.00048"},{"key":"ref164","article-title":"Encouraging divergent thinking in large language models through multi-agent debate","author":"Liang","year":"2023","journal-title":"arXiv:2305.19118"},{"key":"ref165","article-title":"LLM-assist: Enhancing closed-loop planning with language-based reasoning","author":"Sharan","year":"2023","journal-title":"arXiv:2401.00125"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref167","article-title":"GPT-driver: Learning to drive with GPT","author":"Mao","year":"2023","journal-title":"arXiv:2310.01415"},{"key":"ref168","article-title":"Collaborating with language models for embodied reasoning","author":"Dasgupta","year":"2023","journal-title":"arXiv:2302.00763"},{"key":"ref169","article-title":"Zero-shot goal-directed dialogue via RL on imagined conversations","author":"Hong","year":"2023","journal-title":"arXiv:2311.05584"},{"key":"ref170","article-title":"Communicative agents for software development","author":"Qian","year":"2023","journal-title":"arXiv:2307.07924"},{"key":"ref171","article-title":"Unicron: Economizing self-healing LLM training at scale","author":"He","year":"2023","journal-title":"arXiv:2401.00134"},{"key":"ref172","article-title":"Exploring the robustness of decentralized training for large language models","author":"Lu","year":"2023","journal-title":"arXiv:2312.00843"},{"key":"ref173","first-page":"25464","article-title":"Decentralized training of foundation models in heterogeneous environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yuan"},{"key":"ref174","article-title":"Swarm parallelism: Training large models can be surprisingly communication-efficient","author":"Ryabinin","year":"2023","journal-title":"arXiv:2301.11913"},{"key":"ref175","first-page":"36058","article-title":"CocktailSGD: Fine-tuning foundation models over 500Mbps networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref176","article-title":"GradientCoin: A peer-to-peer decentralized large language models","author":"Gao","year":"2023","journal-title":"arXiv:2308.10502"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref178","article-title":"Knowledge distillation of large language models","author":"Gu","year":"2023","journal-title":"arXiv:2306.08543"},{"key":"ref179","article-title":"Adaptive intellect unleashed: The feasibility of knowledge transfer in large language models","author":"Huang","year":"2023","journal-title":"arXiv:2308.04788"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICC51166.2024.10623108"},{"key":"ref181","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref182","first-page":"1","article-title":"CTR-BERT: Cost-effective knowledge distillation for billion-parameter teacher models","volume-title":"Proc. NeurIPS Efficient Natural Lang. Speech Process. Workshop","author":"Muhamed"},{"key":"ref183","article-title":"TinyLLM: Learning a small student from multiple large language models","author":"Tian","year":"2024","journal-title":"arXiv:2402.04616"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sustainlp-1.3"},{"key":"ref185","article-title":"DistiLLM: Towards streamlined distillation for large language models","author":"Ko","year":"2024","journal-title":"arXiv:2402.03898"},{"key":"ref186","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei"},{"key":"ref187","first-page":"21","article-title":"Is it an agent, or just a program? A taxonomy for autonomous agents","volume-title":"Proc. Int. Workshop Agent Theories, Archit., Languages","author":"Franklin"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003432"},{"issue":"1","key":"ref189","first-page":"62","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27","volume":"62","author":"LeCun","year":"2022","journal-title":"Open Rev."},{"key":"ref190","article-title":"A survey on large language model based autonomous agents","author":"Wang","year":"2023","journal-title":"arXiv:2308.11432"},{"key":"ref191","article-title":"Multi-agent collaboration: Harnessing the power of intelligent LLM agents","author":"Talebirad","year":"2023","journal-title":"arXiv:2306.03314"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref193","article-title":"Balancing autonomy and alignment: A multi-dimensional taxonomy for autonomous LLM-powered multi-agent architectures","author":"H\u00e4ndler","year":"2023","journal-title":"arXiv:2310.03659"},{"key":"ref194","article-title":"Palm 2 technical report","volume-title":"arXiv:2305.10403","author":"Anil","year":"2023"},{"issue":"240","key":"ref195","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref196","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kojima"},{"key":"ref197","article-title":"Benchmarks for RL on goal-directed language tasks with LLMs","volume-title":"Proc. Electr. Eng. Comput. Sci.","author":"Sun","year":"2023"},{"key":"ref198","article-title":"AutoGEN: Enabling next-gen LLM applications via multi-agent conversation framework","author":"Wu","year":"2023","journal-title":"arXiv:2308.08155"},{"key":"ref199","article-title":"Empowering autonomous driving with large language models: A safety perspective","author":"Wang","year":"2023","journal-title":"arXiv:2312.00812"},{"key":"ref200","article-title":"Prompt cache: Modular attention reuse for low-latency inference","author":"Gim","year":"2023","journal-title":"arXiv:2311.04934"},{"key":"ref201","article-title":"Cache & distil: Optimising API calls to large language models","author":"Ram\u00edrez","year":"2023","journal-title":"arXiv:2310.13561"},{"key":"ref202","article-title":"Harnessing scalable transactional stream processing for managing large language models [vision]","author":"Zhang","year":"2023","journal-title":"arXiv:2307.08225"},{"key":"ref203","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023","journal-title":"arXiv:2309.17453"},{"key":"ref204","article-title":"LLMCad: Fast and scalable on-device large language model inference","author":"Xu","year":"2023","journal-title":"arXiv:2309.04255"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3610856"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref207","article-title":"SparQ attention: Bandwidth-efficient LLM inference","author":"Ribar","year":"2023","journal-title":"arXiv:2312.04985"},{"key":"ref208","article-title":"LLM in a flash: Efficient large language model inference with limited memory","author":"Alizadeh","year":"2023","journal-title":"arXiv:2312.11514"},{"key":"ref209","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","author":"Frantar","year":"2023","journal-title":"arXiv:2301.00774"},{"key":"ref210","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref211","article-title":"Agile-quant: Activation-guided quantization for faster inference of LLMs on the edge","author":"Shen","year":"2023","journal-title":"arXiv:2312.05693"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3091575"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700246"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref215","volume-title":"Optimized network architectures for training large language models with billions of parameters","author":"Wang","year":"2023"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00174"},{"key":"ref217","article-title":"The rise and potential of large language model based agents: A survey","author":"Xi","year":"2023","journal-title":"arXiv:2309.07864"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1145\/3643915.3644088"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref220","first-page":"1","article-title":"Towards large language models at the edge on mobile, augmented reality, and virtual reality devices with unity","volume-title":"Proc. Syst. Archit. Gener. AI Edge\/Mobile Platforms (SAGE)","author":"Morales"},{"key":"ref221","article-title":"Multi-frame, lightweight & efficient vision-language models for question answering in autonomous driving","author":"Gopalkrishnan","year":"2024","journal-title":"arXiv:2403.19838"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adi8500"},{"key":"ref223","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023","journal-title":"arXiv:2306.13549"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2100338"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref228","article-title":"LLM-QAT: Data-free quantization aware training for large language models","author":"Liu","year":"2023","journal-title":"arXiv:2305.17888"},{"key":"ref229","first-page":"7750","article-title":"The case for 4-bit precision: K-bit inference scaling laws","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dettmers"},{"key":"ref230","article-title":"Efficient quantization-aware training with adaptive coreset selection","author":"Huang","year":"2023","journal-title":"arXiv:2306.07215"},{"key":"ref231","article-title":"PB-LLM: Partially binarized large language models","author":"Shang","year":"2023","journal-title":"arXiv:2310.00034"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800608"},{"key":"ref234","article-title":"Wireless multi-agent generative AI: From connected intelligence to collective intelligence","author":"Zou","year":"2023","journal-title":"arXiv:2307.02757"},{"key":"ref235","article-title":"Large language models for telecom: The next big thing?","author":"Bariah","year":"2023","journal-title":"arXiv:2306.10249"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2000409"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/6GSUMMIT49458.2020.9083851"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1080\/03772063.2022.2048705"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2934385"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3015762"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10570588"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2019.2963091"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107520"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13030549"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.005.2200905"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC61514.2024.10592587"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108565"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2023.3346824"},{"key":"ref249","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446717"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1145\/3582515.3609536"},{"key":"ref252","article-title":"Enabling waypoint generation for collaborative robots using LLMs and mixed reality","author":"Fang","year":"2024","journal-title":"arXiv:2403.09308"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2022.3195219"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3317242"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac409"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900534"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2921162"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2020.3010270"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56066-8_1"},{"key":"ref260","article-title":"Understanding is compression","author":"Li","year":"2024","journal-title":"arXiv:2407.07723"},{"key":"ref261","article-title":"A framework for cost-effective and self-adaptive LLM shaking and recovery mechanism","author":"Chen","year":"2024","journal-title":"arXiv:2403.07283"},{"key":"ref262","article-title":"DriveGPT4: Interpretable end-to-end autonomous driving via large language model","author":"Xu","year":"2023","journal-title":"arXiv:2310.01412"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.3390\/s23229225"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogr.2023.04.001"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3327715"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581045"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2007.41"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00107"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00108"},{"key":"ref273","article-title":"Large language models for autonomous driving: Real-world experiments","author":"Cui","year":"2023","journal-title":"arXiv:2312.09397"},{"key":"ref274","article-title":"HiLM-D: Towards high-resolution understanding in multimodal large language models for autonomous driving","author":"Ding","year":"2023","journal-title":"arXiv:2309.05186"},{"key":"ref275","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1561\/0600000079"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00141"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.133"},{"key":"ref279","volume-title":"Model S owners manual","year":"2024"},{"key":"ref280","volume-title":"Baidu Apollo project repository","year":"2024"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2841349"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3349324"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114134"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1145\/3505243"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-FoSE59343.2023.00008"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1145\/3383458"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/iSemantic59612.2023.10295323"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/APR59189.2023.00012"},{"key":"ref289","article-title":"A new era in software security: Towards self-healing software via large language models and formal verification","author":"Charalambous","year":"2023","journal-title":"arXiv:2305.14752"},{"key":"ref290","first-page":"191","article-title":"Towards LLM-based system migration in language-driven engineering","volume-title":"Proc. Int. Conf. Eng. Comput.-Based Syst.","author":"Busch"},{"key":"ref291","article-title":"The scope of ChatGPT in software engineering: A thorough investigation","author":"Ma","year":"2023","journal-title":"arXiv:2305.12138"},{"key":"ref292","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv:2107.03374"},{"key":"ref293","article-title":"Self-collaboration code generation via ChatGPT","author":"Dong","year":"2023","journal-title":"arXiv:2304.07590"},{"key":"ref294","article-title":"No more manual tests? Evaluating and improving ChatGPT for unit test generation","author":"Yuan","year":"2023","journal-title":"arXiv:2305.04207"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1186\/s13174-018-0087-2"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-023-00980-9"},{"key":"ref297","article-title":"Generative AI-aided optimization for AI-generated content (AIGC) services in edge networks","author":"Du","year":"2023","journal-title":"arXiv:2303.13052"},{"key":"ref298","article-title":"LLM-assisted light: Leveraging large language model capabilities for human-mimetic traffic signal control in complex urban environments","author":"Wang","year":"2024","journal-title":"arXiv:2403.08337"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/WoWMoM.2014.6918985"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1145\/2620728.2620744"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0335-9"},{"key":"ref302","first-page":"301","article-title":"Doctor AI: Predicting clinical events via recurrent neural networks","volume-title":"Proc. Mach. Learn. Healthc. Conf.","author":"Choi"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.2991043"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1549"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.abb1655"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00742-2"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.2196\/45312"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01024-9"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00370-1"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3206782"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51999-5_32"},{"key":"ref314","article-title":"Large language models for software engineering: A systematic literature review","author":"Hou","year":"2023","journal-title":"arXiv:2308.10620"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3368208"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref317","article-title":"SQL-PaLM: Improved large language model adaptation for text-to-SQL","author":"Sun","year":"2023","journal-title":"arXiv:2306.00739"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0088-2"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1038\/s41563-019-0345-0"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref321","article-title":"Scalable multi-robot collaboration with large language models: Centralized or Decentralized systems?","author":"Chen","year":"2023","journal-title":"arXiv:2309.15943"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626869"},{"key":"ref324","article-title":"BloombergGPT: A large language model for finance","author":"Wu","year":"2023","journal-title":"arXiv:2303.17564"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.64"},{"key":"ref326","article-title":"Application of LLM agents in recruitment: A novel framework for resume screening","author":"Gan","year":"2024","journal-title":"arXiv:2401.08315"},{"key":"ref327","article-title":"GPTVoiceTasker: LLM-powered virtual assistant for smartphone","author":"Vu","year":"2024","journal-title":"arXiv:2401.14268"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623985"},{"key":"ref329","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"ref330","article-title":"Scalable extraction of training data from (production) language models","author":"Nasr","year":"2023","journal-title":"arXiv:2311.17035"},{"key":"ref331","article-title":"Jailbroken: How does LLM safety training fail?","author":"Wei","year":"2023","journal-title":"arXiv:2307.02483"},{"key":"ref332","article-title":"`Do anything now,\u201d: Characterizing and evaluating in-the-wild jailbreak prompts on large language models","author":"Shen","year":"2023","journal-title":"arXiv:2308.03825"},{"key":"ref333","first-page":"2633","article-title":"Extracting training data from large language models","volume-title":"Proc. 30th USENIX Secur. Symp. (USENIX Security)","author":"Carlini"},{"key":"ref334","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-018-9482-5"},{"key":"ref336","article-title":"Backdoor attacks for in-context learning with language models","author":"Kandpal","year":"2023","journal-title":"arXiv:2307.14692"},{"key":"ref337","article-title":"Data poisoning for in-context learning","author":"He","year":"2024","journal-title":"arXiv:2402.02160"},{"key":"ref338","article-title":"A LLM assisted exploitation of AI-guardian","author":"Carlini","year":"2023","journal-title":"arXiv:2307.15008"},{"key":"ref339","article-title":"A comprehensive overview of backdoor attacks in large language models within communication networks","author":"Yang","year":"2023","journal-title":"arXiv:2308.14367"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.757"},{"key":"ref341","article-title":"Prompt injection attacks and defenses in LLM-integrated applications","author":"Liu","year":"2023","journal-title":"arXiv:2310.12815"},{"key":"ref342","article-title":"LLM jailbreak attack versus defense techniques\u2014A comprehensive study","author":"Xu","year":"2024","journal-title":"arXiv:2402.13457"},{"key":"ref343","article-title":"Tree of attacks: Jailbreaking black-box LLMs automatically","author":"Mehrotra","year":"2023","journal-title":"arXiv:2312.02119"},{"key":"ref344","article-title":"MasterKey: Automated jailbreak across multiple large language model chatbots","author":"Deng","year":"2023","journal-title":"arXiv:2307.08715"},{"key":"ref345","article-title":"Evil geniuses: Delving into the safety of LLM-based agents","author":"Tian","year":"2023","journal-title":"arXiv:2311.11855"},{"key":"ref346","article-title":"Beyond memorization: Violating privacy via inference with large language models","author":"Staab","year":"2023","journal-title":"arXiv:2310.07298"},{"key":"ref347","article-title":"Training data leakage analysis in language models","author":"Inan","year":"2021","journal-title":"arXiv:2101.05405"},{"key":"ref348","article-title":"RatGPT: Turning online LLMs into proxies for malware attacks","author":"Beckerich","year":"2023","journal-title":"arXiv:2308.09183"},{"key":"ref349","article-title":"A new era in LLM security: Exploring security concerns in real-world LLM-based systems","author":"Wu","year":"2024","journal-title":"arXiv:2402.18649"},{"key":"ref350","article-title":"LLM platform security: Applying a systematic evaluation framework to OpenAIs ChatGPT plugins","author":"Iqbal","year":"2023","journal-title":"arXiv:2309.10254"},{"key":"ref351","article-title":"Privacy issues in large language models: A survey","author":"Neel","year":"2023","journal-title":"arXiv:2312.06717"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2019.2897554"},{"key":"ref353","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref354","first-page":"1","article-title":"User inference attacks on LLMs","volume-title":"Proc. Soc. Respons. Lang. Model. Res.","author":"Kandpal"},{"key":"ref355","first-page":"1","article-title":"Membership inference attacks against NLP classification models","volume-title":"Proc. Workshop Privacy Mach. Learn.","author":"Shejwalkar"},{"key":"ref356","article-title":"A theoretical insight into attack and defense of gradient leakage in transformer","author":"Li","year":"2023","journal-title":"arXiv:2311.13624"},{"key":"ref357","volume-title":"A survey on large language models: Applications, challenges, limitations, and practical usage","author":"Hadi","year":"2023"},{"key":"ref358","article-title":"Large language models can be strong differentially private learners","author":"Li","year":"2021","journal-title":"arXiv:2110.05679"},{"key":"ref359","article-title":"Building trust in conversational AI: A comprehensive review and solution architecture for explainable, privacy-aware systems using LLMs and knowledge graph","author":"Zafar","year":"2023","journal-title":"arXiv:2308.13534"},{"key":"ref360","first-page":"396","article-title":"Synergistic integration of large language models and cognitive architectures for robust AI: An exploratory analysis","volume-title":"Proc. AAAI Symp. Ser.","author":"Romero"},{"key":"ref361","article-title":"Whispers in the machine: Confidentiality in LLM-integrated systems","author":"Evertz","year":"2024","journal-title":"arXiv:2402.06922"},{"key":"ref362","article-title":"CyberMetric: A benchmark dataset for evaluating large language models knowledge in cybersecurity","author":"Tihanyi","year":"2024","journal-title":"arXiv:2402.07688"},{"key":"ref363","first-page":"10697","article-title":"Deduplicating training data mitigates privacy risks in language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kandpal"},{"key":"ref364","article-title":"Datasets for large language models: A comprehensive survey","author":"Liu","year":"2024","journal-title":"arXiv:2402.18041"},{"key":"ref365","article-title":"CCNet: Extracting high quality monolingual datasets from web crawl data","author":"Wenzek","year":"2019","journal-title":"arXiv:1911.00359"},{"key":"ref366","article-title":"Defending jailbreak prompts via in-context adversarial game","author":"Zhou","year":"2024","journal-title":"arXiv:2402.13148"},{"key":"ref367","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.484"},{"key":"ref368","article-title":"Round trip translation defence against large language model jailbreaking attacks","author":"Yung","year":"2024","journal-title":"arXiv:2402.13517"},{"key":"ref369","article-title":"Baseline defenses for adversarial attacks against aligned language models","author":"Jain","year":"2023","journal-title":"arXiv:2309.00614"},{"key":"ref370","article-title":"StruQ: Defending against prompt injection with structured queries","author":"Chen","year":"2024","journal-title":"arXiv:2402.06363"},{"key":"ref371","article-title":"The art of defending: A systematic evaluation and analysis of LLM defense strategies on safety and over-defensiveness","author":"Varshney","year":"2023","journal-title":"arXiv:2401.00287"},{"key":"ref372","article-title":"Detection and defense against prominent attacks on preconditioned LLM-integrated virtual assistants","author":"Chan","year":"2024","journal-title":"arXiv:2401.00994"},{"key":"ref373","first-page":"1685","article-title":"Towards a proactive ML approach for detecting backdoor poison samples","volume-title":"Proc. 32nd USENIX Security Symp. (USENIX Security)","author":"Qi"},{"key":"ref374","article-title":"LLM self defense: By self examination, LLMs know they are being tricked","author":"Helbling","year":"2023","journal-title":"arXiv:2308.07308"},{"key":"ref375","article-title":"Defending LLMs against jailbreaking attacks via backtranslation","author":"Wang","year":"2024","journal-title":"arXiv:2402.16459"},{"key":"ref376","first-page":"1","article-title":"Defending pre-trained language models as few-shot learners against backdoor attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xi"},{"key":"ref377","article-title":"Detecting language model attacks with perplexity","author":"Alon","year":"2023","journal-title":"arXiv:2308.14132"},{"key":"ref378","article-title":"Token-level adversarial prompt detection based on perplexity measures and contextual information","author":"Hu","year":"2023","journal-title":"arXiv:2311.11509"},{"key":"ref379","doi-asserted-by":"publisher","DOI":"10.1145\/3605760.3623764"},{"key":"ref380","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-3679775\/v1","volume-title":"Efficient ransomware detection via portable executable file image analysis by LLaMA-7b","author":"Li","year":"2023"},{"key":"ref381","doi-asserted-by":"publisher","DOI":"10.52306\/2578-3289.1172"},{"key":"ref382","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7584-6_21"},{"key":"ref383","article-title":"Can large language models find and fix vulnerable software?","author":"Noever","year":"2023","journal-title":"arXiv:2308.10345"},{"key":"ref384","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00065"},{"key":"ref385","article-title":"PentestGPT: An LLM-empowered automatic penetration testing tool","author":"Deng","year":"2023","journal-title":"arXiv:2308.06782"},{"key":"ref386","article-title":"AutoAttacker: A large language model guided system to implement automatic cyber-attacks","author":"Xu","year":"2024","journal-title":"arXiv:2403.01038"},{"key":"ref387","article-title":"Employing LLMs for incident response planning and review","author":"Hays","year":"2024","journal-title":"arXiv:2403.01271"},{"key":"ref388","article-title":"LOCALINTEL: Generating organizational threat intelligence from global and local cyber knowledge","author":"Mitra","year":"2024","journal-title":"arXiv:2401.10036"},{"key":"ref389","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-3970015\/v1","volume-title":"Applications of LLMs for generating cyber security exercise scenarios","author":"Yamin","year":"2024"},{"key":"ref390","article-title":"Synthetic data in AI: Challenges, applications, and ethical implications","author":"Hao","year":"2024","journal-title":"arXiv:2401.01629"},{"key":"ref391","doi-asserted-by":"publisher","DOI":"10.1145\/3617555.3617874"},{"key":"ref392","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179473"},{"key":"ref393","doi-asserted-by":"publisher","DOI":"10.1007\/s12525-022-00593-5"},{"key":"ref394","doi-asserted-by":"publisher","DOI":"10.14722\/usec.2022.23014"},{"key":"ref395","article-title":"HuntGPT: Integrating machine learning-based anomaly detection and explainable AI with large language models (LLMs)","author":"Ali","year":"2023","journal-title":"arXiv:2309.16021"},{"key":"ref396","doi-asserted-by":"publisher","DOI":"10.1109\/COGSIMA.2015.7108194"},{"key":"ref397","article-title":"KoLA: Carefully benchmarking world knowledge of large language models","author":"Yu","year":"2023","journal-title":"arXiv:2306.09296"},{"key":"ref398","volume-title":"Considerations for evaluating large language models for cybersecurity tasks","author":"Gennari","year":"2024"},{"key":"ref399","article-title":"An empirical evaluation of LLMs for solving offensive security challenges","author":"Shao","year":"2024","journal-title":"arXiv:2402.11814"},{"key":"ref400","first-page":"1","article-title":"CyberBench: A multi-task benchmark for evaluating large language models in cybersecurity","volume-title":"Proc. Workshop Artif. Intell. Cyber Secur. (AICS)","author":"Liu"},{"key":"ref401","article-title":"SecQA: A concise question-answering dataset for evaluating large language models in computer security","author":"Liu","year":"2023","journal-title":"arXiv:2312.15838"},{"key":"ref402","article-title":"How well does LLM generate security tests?","author":"Zhang","year":"2023","journal-title":"arXiv:2310.00710"},{"key":"ref403","volume-title":"LLaMa assisted reverse engineering of modern ransomware: A comparative analysis with early crypto-ransomware","author":"Vasconcelos","year":"2023"},{"key":"ref404","article-title":"Shifting the lens: Detecting malware in NPM ecosystem with large language models","author":"Zahan","year":"2024","journal-title":"arXiv:2403.12196"},{"key":"ref405","article-title":"Purple llama CyberSeceval: A secure coding benchmark for language models","author":"Bhatt","year":"2023","journal-title":"arXiv:2312.04724"},{"key":"ref406","article-title":"Towards trustable language models: Investigating information quality of large language models","author":"Rejeleene","year":"2024","journal-title":"arXiv:2401.13086"},{"key":"ref407","article-title":"Usable XAI: 10 strategies towards exploiting explainability in the LLM era","author":"Wu","year":"2024","journal-title":"arXiv:2403.08946"},{"key":"ref408","article-title":"AI transparency in the age of LLMs: A human-centered research roadmap","author":"Liao","year":"2023","journal-title":"arXiv:2306.01941"},{"key":"ref409","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-023-10179-8"},{"key":"ref410","article-title":"Understanding adversary behavior via XAI: Leveraging sequence clustering to extract threat intelligence","author":"Nadeem","year":"2024"},{"key":"ref411","article-title":"Bias in generative AI","author":"Zhou","year":"2024","journal-title":"arXiv:2403.02726"},{"key":"ref412","doi-asserted-by":"publisher","DOI":"10.3390\/e23010018"},{"key":"ref413","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"ref414","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3180184"},{"key":"ref415","article-title":"Detectors for safe and reliable LLMs: Implementations, uses, and limitations","author":"Achintalwar","year":"2024","journal-title":"arXiv:2403.06009"},{"key":"ref416","article-title":"Few-shot fairness: Unveiling LLMs potential for fairness-aware classification","author":"Chhikara","year":"2024","journal-title":"arXiv:2402.18502"},{"key":"ref417","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608860"},{"key":"ref418","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-022-00137-9"},{"issue":"1","key":"ref419","doi-asserted-by":"crossref","first-page":"1","DOI":"10.33140\/EOA.01.02.10","article-title":"Detecting propaganda in news articles using large language models","volume":"2","author":"Jones","year":"2024","journal-title":"Eng. Open Access"},{"key":"ref420","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00476"},{"key":"ref421","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00765-8"},{"key":"ref422","article-title":"Defending against alignment-breaking attacks via robustly aligned LLM","author":"Cao","year":"2023","journal-title":"arXiv:2309.14348"},{"key":"ref423","article-title":"Certified robustness for large language models with self-denoising","author":"Zhang","year":"2023","journal-title":"arXiv:2307.07171"},{"key":"ref424","volume-title":"Ethics of artificial intelligence and robotics","author":"M\u00fcller","year":"2020"},{"key":"ref425","first-page":"1","article-title":"Towards publicly accountable frontier LLMs","volume-title":"Proc. Soc. Respons. Lang. Model. Res.","author":"Anderljung"},{"key":"ref426","article-title":"The ethics of interaction: Mitigating security threats in LLMs","author":"Kumar","year":"2024","journal-title":"arXiv:2401.12273"},{"key":"ref427","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc7010015"},{"key":"ref428","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon60102.2023.10255221"},{"key":"ref429","volume-title":"neuroGPT-X: Towards an accountable expert opinion tool for vestibular schwannoma","author":"Guo","year":"2023"},{"key":"ref430","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372873"},{"key":"ref431","doi-asserted-by":"publisher","DOI":"10.1145\/3419764"},{"key":"ref432","article-title":"The malicious use of artificial intelligence: Forecasting, prevention, and mitigation","author":"Brundage","year":"2018","journal-title":"arXiv:1802.07228"},{"key":"ref433","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-024-00426-z"},{"key":"ref434","article-title":"Cached model-as-a-resource: Provisioning large language model agents for edge intelligence in space-air-ground integrated networks","author":"Xu","year":"2024","journal-title":"arXiv:2403.05826"},{"key":"ref435","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guu"},{"key":"ref436","article-title":"Continual learning for large language models: A survey","author":"Wu","year":"2024","journal-title":"arXiv:2402.01364"},{"key":"ref437","volume-title":"Efficiently scale LLM training across a large GPU cluster with Alpa and ray.","author":"Jiao Dong","year":"2024"},{"key":"ref438","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref439","article-title":"Zero trust architecture","author":"Stafford","year":"2020"},{"key":"ref440","doi-asserted-by":"publisher","DOI":"10.1016\/j.csi.2024.103832"},{"key":"ref441","article-title":"Decoding compressed trust: Scrutinizing the trustworthiness of efficient LLMs under compression","author":"Hong","year":"2024","journal-title":"arXiv:2403.15447"},{"key":"ref442","doi-asserted-by":"publisher","DOI":"10.1109\/FiCloud.2017.49"},{"key":"ref443","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103278"},{"key":"ref444","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.04.057"},{"key":"ref445","article-title":"AI-native interconnect framework for integration of large language model technologies in 6G systems","author":"Tarkoma","year":"2023","journal-title":"arXiv:2311.05842"},{"key":"ref446","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3293055"},{"key":"ref447","volume-title":"Reduce the Attack Surface Around Your Data to Unlock New Opportunities","year":"2024"},{"key":"ref448","doi-asserted-by":"publisher","DOI":"10.1201\/9781003109952-5"},{"key":"ref449","doi-asserted-by":"publisher","DOI":"10.3390\/app13031252"},{"key":"ref450","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"ref451","article-title":"Are language models actually useful for time series forecasting?","author":"Tan","year":"2024","journal-title":"arXiv:2406.16964"},{"key":"ref452","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref453","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref454","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599572"},{"key":"ref455","article-title":"Large language models for supply chain optimization","author":"Li","year":"2023","journal-title":"arXiv:2307.03875"},{"key":"ref456","first-page":"1","article-title":"Amazon-M2: A multilingual multi-locale shopping session dataset for recommendation and text generation","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","volume":"36","author":"Jin"},{"key":"ref457","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661357"},{"key":"ref458","article-title":"PerceptionGPT: Effectively fusing visual perception into LLM","author":"Pi","year":"2023","journal-title":"arXiv:2311.06612"}],"container-title":["IEEE Open Journal of the Communications Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782661\/10362961\/10669603.pdf?arnumber=10669603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T06:29:48Z","timestamp":1726813788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10669603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":458,"URL":"https:\/\/doi.org\/10.1109\/ojcoms.2024.3456549","relation":{},"ISSN":["2644-125X"],"issn-type":[{"value":"2644-125X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}