{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:18Z","timestamp":1763191698917,"version":"3.45.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227336","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Attack on Large Language Models using Exponentiated Gradient Descent"],"prefix":"10.1109","author":[{"given":"Sajib","family":"Biswas","sequence":"first","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]},{"given":"Mao","family":"Nishino","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Mathematics,Tallahassee,Florida"}]},{"given":"Samuel Jacob","family":"Chacko","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]},{"given":"Xiuwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlpcss-1.24"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-024-02046-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-023-00339-9"},{"key":"ref6","article-title":"Ethical and social risks of harm from language models. arxiv","volume":"10","author":"Weidinger","year":"2021"},{"key":"ref7","first-page":"2633","article-title":"Extracting training data from large language models","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini"},{"key":"ref8","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"17506","article-title":"Pretraining language models with human preferences","volume-title":"International Conference on Machine Learning","author":"Korbak"},{"article-title":"Rain: Your language models can align themselves without finetuning","year":"2023","author":"Li","key":"ref10"},{"article-title":"Jailbreaker: Automated jailbreak across multiple large language model chatbots","year":"2023","author":"Deng","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/satml64287.2025.00010"},{"article-title":"Intriguing properties of neural networks","year":"2013","author":"Szegedy","key":"ref13"},{"article-title":"Explaining and harnessing adversarial examples","year":"2014","author":"Goodfellow","key":"ref14"},{"key":"ref15","article-title":"Jailbroken: How does llm safety training fail?","volume":"36","author":"Wei","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7962-2_30"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref18","article-title":"Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery","volume":"36","author":"Wen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Are aligned neural networks adversarially aligned?","volume":"36","author":"Carlini","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Catastrophic jailbreak of open-source llms via exploiting generation","year":"2023","author":"Huang","key":"ref20"},{"article-title":"Universal and transferable adversarial attacks on aligned language models","year":"2023","author":"Zou","key":"ref21"},{"article-title":"Fast adversarial attacks on language models in one gpu minute","year":"2024","author":"Sadasivan","key":"ref22"},{"article-title":"Attacking large language models with projected gradient descent","year":"2024","author":"Geisler","key":"ref23"},{"article-title":"Soft prompt threats: Attacking safety alignment and unlearning in open-source llms through the embedding space","year":"2024","author":"Schwinn","key":"ref24"},{"article-title":"Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shayegani","key":"ref25"},{"article-title":"Assessing adversarial robustness of large language models: An empirical study","year":"2024","author":"Yang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892426"},{"article-title":"Large language models as superpositions of cultural perspectives","year":"2023","author":"Kova\u010d","key":"ref28"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1221"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-2006"},{"article-title":"Amplegcg: Learning a universal and transferable generative model of adversarial suffixes for jailbreaking both open and closed llms","year":"2024","author":"Liao","key":"ref32"},{"article-title":"Towards deep learning models resistant to adversarial attacks","year":"2017","author":"Madry","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390191"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2016.7795300"},{"issue":"1","key":"ref36","first-page":"1","article-title":"Exponentiated gradient versus gradient descent for linear predictors","volume-title":"Information and Computation","volume":"132","author":"Kivinen","year":"1997"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115889"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref38"},{"issue":"3","key":"ref39","first-page":"200","article-title":"The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming","volume-title":"USSR Computational Mathematics and Mathematical Physics","volume":"7","author":"Bregman","year":"1967"},{"article-title":"Iterative bregman projections for regularized transportation problems","year":"2014","author":"Benamou","key":"ref40"},{"article-title":"An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions","year":"2014","author":"Bot","key":"ref41"},{"article-title":"Computational optimal transport","year":"2020","author":"Peyr\u00e9","key":"ref42"},{"article-title":"The falcon series of open language models","year":"2023","author":"Almazrouei","key":"ref43"},{"first-page":"05","article-title":"Introducing mpt-7b: A new standard for open-source, commercially usable llms, 2023","year":"2023","key":"ref44"},{"article-title":"Mistral 7b","year":"2023","author":"Jiang","key":"ref45"},{"key":"ref46","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"The llama 3 herd of models","year":"2024","author":"Dubey","key":"ref47"},{"article-title":"Safe rlhf: Safe reinforcement learning from human feedback","year":"2023","author":"Dai","key":"ref48"},{"article-title":"Harmbench: A standardized evaluation framework for automated red teaming and robust refusal","year":"2024","author":"Mazeika","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1745"},{"article-title":"Adversarial attacks on large language models using regularized relaxation","year":"2024","author":"Chacko","key":"ref51"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227336.pdf?arnumber=11227336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:25:04Z","timestamp":1763191504000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227336","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}