{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:21:19Z","timestamp":1776082879840,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":112,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"U.S. Army Research Office","award":["MURI grant W911NF-21-1-0317"],"award-info":[{"award-number":["MURI grant W911NF-21-1-0317"]}]},{"name":"Future Enterprise Security Initiative at Carnegie Mellon CyLab (FutureEnterprise@CyLab)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,26]]},"DOI":"10.1145\/3706598.3714025","type":"proceedings-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T03:30:09Z","timestamp":1745465409000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6759-6499","authenticated-orcid":false,"given":"Weiran","family":"Lin","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3135-3431","authenticated-orcid":false,"given":"Anna","family":"Gerchanovsky","sequence":"additional","affiliation":[{"name":"Duke University, Durham, North Carolina, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5156-6925","authenticated-orcid":false,"given":"Omer","family":"Akgul","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8209-6792","authenticated-orcid":false,"given":"Lujo","family":"Bauer","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1820-1698","authenticated-orcid":false,"given":"Matt","family":"Fredrikson","sequence":"additional","affiliation":[{"name":"Carnegie Mellon, Pittsburgh, Pennsylvania, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6233-2120","authenticated-orcid":false,"given":"Zifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Scale AI, San Francisco, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_3_2_2","volume-title":"SOUPS 2021: USENIX Symposium on Usable Privacy and Security","author":"Abrokwa Desiree","year":"2021","unstructured":"Desiree Abrokwa, Shruti Das, Omer Akgul, and Michelle\u00a0L Mazurek. 2021. Comparing Security and Privacy Attitudes Between iOS and Android Users in the US. In SOUPS 2021: USENIX Symposium on Usable Privacy and Security."},{"key":"e_1_3_3_3_3_2","unstructured":"Jina AI. 2024. PromptPerfect - AI prompt generator and optimizer. https:\/\/promptperfect.jina.ai\/ Accessed: 2024-06-06."},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"crossref","unstructured":"Shahriar Akter Yogesh\u00a0K Dwivedi Shahriar Sajib Kumar Biswas Ruwan\u00a0J Bandara and Katina Michael. 2022. Algorithmic Bias in Machine Learning-Based Marketing Models. Journal of Business Research 144 (2022).","DOI":"10.1016\/j.jbusres.2022.01.083"},{"key":"e_1_3_3_3_5_2","unstructured":"Anthropic. 2024. Automatically Generate First Draft Prompt Templates. https:\/\/docs.anthropic.com\/en\/docs\/build-with-claude\/prompt-engineering\/prompt-generator. Accessed: 2024-09-07."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Kalya\u00a0Win Aung Ewan Soubutts and Aneesha Singh. 2024. \"What a stupid way to do business\": Towards an Understanding of Older Adults\u2019 Perceptions of Deceptive Patterns and Ways to Develop Resistance. Proc. ACM Hum.-Comput. Interact. (2024). 10.1145\/3677113","DOI":"10.1145\/3677113"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/SecDev.2019.00016"},{"key":"e_1_3_3_3_8_2","volume-title":"Twentieth Symposium on Usable Privacy and Security (SOUPS 2024)","author":"Balash David\u00a0G","year":"2024","unstructured":"David\u00a0G Balash, Mir\u00a0Masood Ali, Chris Kanich, and Adam\u00a0J Aviv. 2024. \" I would not install an app with this label\": Privacy Label Impact on Risk Perception and Willingness to Install { iOS} Apps. In Twentieth Symposium on Usable Privacy and Security (SOUPS 2024)."},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Yoav Benjamini and Yosef Hochberg. 1995. Controlling the False Discovery Rate: a Practical and Powerful Approach to Multiple Testing. Journal of the Royal Statistical Society: Series B (Methodological) (1995).","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3516502"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Christoph B\u00f6sch Benjamin Erb Frank Kargl Henning Kopp and Stefan Pfattheicher. 2016. Tales from the Dark Side: Privacy Dark Strategies and Privacy Dark Patterns. Proceedings on Privacy Enhancing Technologies4 (2016).","DOI":"10.1515\/popets-2016-0038"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2501604.2501610"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Rafael\u00a0A Calvo Dorian Peters Karina Vold and Richard\u00a0M Ryan. 2020. Supporting human autonomy in AI systems: A framework for ethical enquiry. Ethics of Digital Well-Being: A Multidisciplinary Approach (2020).","DOI":"10.1007\/978-3-030-50585-1_2"},{"key":"e_1_3_3_3_15_2","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tram\u00e8r, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, \u00dalfar Erlingsson, Alina Oprea, and Colin Raffel. 2021. Extracting Training Data from Large Language Models. In 30th USENIX Security Symposium (USENIX Security 21)."},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650997"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581258"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3170427.3185377"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173715"},{"key":"e_1_3_3_3_22_2","unstructured":"Alex Cranz. 2024. We have to stop ignoring AI\u2019s hallucination problem. The Verge (2024). https:\/\/www.theverge.com\/2024\/5\/15\/24154808\/ai-chatgpt-google-gemini-microsoft-copilot-hallucination-wrong"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525144"},{"key":"e_1_3_3_3_24_2","unstructured":"Hai Dang Lukas Mecke Florian Lehmann Sven Goller and Daniel Buschek. 2022. How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models. https:\/\/arxiv.org\/abs\/2209.01390"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2016.23390"},{"key":"e_1_3_3_3_26_2","volume-title":"28th USENIX Security Symposium (USENIX Security 19)","author":"Demontis Ambra","year":"2019","unstructured":"Ambra Demontis, Marco Melis, Maura Pintor, Matthew Jagielski, Battista Biggio, Alina Oprea, Cristina Nita-Rotaru, and Fabio Roli. 2019. Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks. In 28th USENIX Security Symposium (USENIX Security 19)."},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2017.8038465"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2006"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Pardis Emami-Naeini Janarth Dheenadhayalan Yuvraj Agarwal and Lorrie\u00a0Faith Cranor. 2022. An Informative Security and Privacy \u201cNutrition\u201d Label for Internet of Things Devices. IEEE Security & Privacy (2022).","DOI":"10.1109\/MSEC.2021.3132398"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.230"},{"key":"e_1_3_3_3_31_2","unstructured":"Expedia. 2023. Expedia launches conversational trip planning powered by ChatGPT to inspire members to dream about travel in new ways. https:\/\/www.expediagroup.com\/investors\/news-and-events\/financial-releases\/news\/news-details\/2023\/Chatgpt-Wrote-This-Press-Release\u2013No-It-Didnt-But-It-Can-Now-Assist-With-Travel-Planning-In-The-Expedia-App\/default.aspx Accessed: 2024-06-05."},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.656"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.31"},{"key":"e_1_3_3_3_34_2","volume-title":"28th USENIX Security Symposium (USENIX Security 19)","author":"Fischer Felix","year":"2019","unstructured":"Felix Fischer, Huang Xiao, Ching-Yu Kao, Yannick Stachelscheid, Benjamin Johnson, Danial Razar, Paul Fawkesley, Nat Buckley, Konstantin B\u00f6ttinger, Paul Muntean, et\u00a0al. 2019. Stack Overflow Considered Helpful! Deep Learning Security Nudges Towards Stronger Cryptography. In 28th USENIX Security Symposium (USENIX Security 19)."},{"key":"e_1_3_3_3_35_2","unstructured":"Isabel\u00a0O Gallegos Ryan\u00a0A Rossi Joe Barrow Md\u00a0Mehrab Tanjim Sungchul Kim Franck Dernoncourt Tong Yu Ruiyi Zhang and Nesreen\u00a0K Ahmed. 2023. Bias and Fairness in Large Language Models: A Survey. https:\/\/arxiv.org\/abs\/2309.00770"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650786"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2017.23313"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.498"},{"key":"e_1_3_3_3_39_2","volume-title":"Scientometrics","author":"Goh Yeow\u00a0Chong","year":"2020","unstructured":"Yeow\u00a0Chong Goh, Xin\u00a0Qing Cai, Walter Theseira, Giovanni Ko, and Khiam\u00a0Aik Khor. 2020. Evaluating Human Versus Machine Learning Performance in Classifying Research Abstracts. In Scientometrics."},{"key":"e_1_3_3_3_40_2","volume-title":"International Conference on Learning Representations","author":"Goodfellow Ian\u00a0J.","year":"2015","unstructured":"Ian\u00a0J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and Harnessing Adversarial Examples. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376142"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174108"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2598510.2598541"},{"key":"e_1_3_3_3_44_2","unstructured":"Yaru Hao Zewen Chi Li Dong and Furu Wei. 2024. Optimizing Prompts for Text-to-Image Generation. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_3_45_2","volume-title":"AAAI Conference on Artificial Intelligence","author":"He Xuanli","year":"2021","unstructured":"Xuanli He, Qiongkai Xu, L. Lyu, Fangzhao Wu, and Chenguang Wang. 2021. Protecting Intellectual Property of Language Generation APIs with Lexical Watermark. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_3_3_46_2","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"He Xuanli","year":"2024","unstructured":"Xuanli He, Qiongkai Xu, Yi Zengt, Lingjuan Lyu, Fangzhao Wu, Jiwei Li, and Ruoxi Jia. 2024. CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks. In Proceedings of the 36th International Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-136"},{"key":"e_1_3_3_3_48_2","unstructured":"Hakan Inan Kartikeya Upasani Jianfeng Chi Rashi Rungta Krithika Iyer Yuning Mao Michael Tontchev Qing Hu Brian Fuller Davide Testuggine and Madian Khabsa. 2024. Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations. (2024)."},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.681"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3503564"},{"key":"e_1_3_3_3_51_2","unstructured":"Joseph R. Biden JR.2023. Executive Order on the Safe Secure and Trustworthy Development and Use of Artificial Intelligence. https:\/\/www.whitehouse.gov\/briefing-room\/presidential-actions\/2023\/10\/30\/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence\/ Accessed: 2024-09-09."},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.707"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/1572532.1572538"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645200"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582269.3615599"},{"key":"e_1_3_3_3_56_2","unstructured":"Aounon Kumar Chirag Agarwal Suraj Srinivas Aaron\u00a0Jiaxun Li Soheil Feizi and Himabindu Lakkaraju. 2024. Certifying LLM Safety against Adversarial Prompting."},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"crossref","unstructured":"Dani\u00ebl Lakens. 2017. Equivalence Tests: A Practical Primer for t Tests Correlations and Meta-Analyses. Social psychological and personality science (2017).","DOI":"10.31234\/osf.io\/97gpc"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70396-6_27"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623120"},{"key":"e_1_3_3_3_60_2","volume-title":"International Conference on Machine Learning","author":"Lin Weiran","year":"2022","unstructured":"Weiran Lin, Keane Lucas, Lujo Bauer, Michael\u00a0K. Reiter, and Mahmood Sharif. 2022. Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks. In International Conference on Machine Learning."},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24084"},{"key":"e_1_3_3_3_62_2","unstructured":"Lowe\u2019s. [n. d.]. Lowe\u2019s Product Expert: Custom GPT. https:\/\/www.lowesinnovationlabs.com\/projects\/lowe-s-product-expert Accessed: 2024-06-05."},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","unstructured":"Jamie Luguri and Lior\u00a0Jacob Strahilevitz. 2021. Shining a Light on Dark Patterns. Journal of Legal Analysis (2021). 10.1093\/jla\/laaa006","DOI":"10.1093\/jla\/laaa006"},{"key":"e_1_3_3_3_64_2","unstructured":"Ben Lutkevich. 2024. 19 of the best large language models in 2024. (2024). https:\/\/www.techtarget.com\/whatis\/feature\/12-of-the-best-large-language-models Accessed: 2024-06-06."},{"key":"e_1_3_3_3_65_2","unstructured":"Dominique Machuletz and Rainer B\u00f6hme. 2019. Multiple Purposes Multiple Problems: A User Study of Consent Dialogs after GDPR. Proceedings on Privacy Enhancing Technologies (2019). https:\/\/api.semanticscholar.org\/CorpusID:201646641"},{"key":"e_1_3_3_3_66_2","volume-title":"International Conference on Learning Representations","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445610"},{"key":"e_1_3_3_3_68_2","volume-title":"Amazon announces Rufus, a new generative AI-powered conversational shopping experience","author":"Mehta Rajiv","year":"2024","unstructured":"Rajiv Mehta and Trishul Chilimbi. 2024. Amazon announces Rufus, a new generative AI-powered conversational shopping experience. https:\/\/www.aboutamazon.com\/news\/retail\/amazon-rufus Accessed: 2024-08-28."},{"key":"e_1_3_3_3_69_2","unstructured":"Microsoft. 2024. Your Everyday AI companion. https:\/\/www.microsoft.com\/en-us\/bing?form=MG0AUO&OCID=MG0AUO Accessed: 2024-06-06."},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.751"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"e_1_3_3_3_72_2","unstructured":"Steven\u00a0Lee Myers. 2025. DeepSeek\u2019s Answers Include Chinese Propaganda Researchers Say. The New York Times (2025). https:\/\/www.nytimes.com\/2025\/01\/31\/technology\/deepseek-chinese-propaganda.html"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376321"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.490"},{"key":"e_1_3_3_3_75_2","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et\u00a0al. 2022. Training Language Models to Follow Instructions with Human Feedback. Advances in Neural Information Processing Systems (2022)."},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24090"},{"key":"e_1_3_3_3_77_2","unstructured":"Pew Research Center. 2024. 2024 pew research center\u2019s american trends panel wave 142 topline. https:\/\/www.pewresearch.org\/wp-content\/uploads\/2024\/03\/SR_24.03.26_chat-bot_topline.pdf"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1561"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.40"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174086"},{"key":"e_1_3_3_3_81_2","unstructured":"Qingyang Ren Zilin Jiang Jinghan Cao Sijia Li Chiqu Li Yiyang Liu Shuning Huo Tiange He and Yuan Chen. 2024. A Survey on Fairness of Large Language Models in E-Commerce: Progress Application and Challenge. https:\/\/arxiv.org\/abs\/2405.13025"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"e_1_3_3_3_83_2","volume-title":"Google AI\u2019s Gemini criticized for generating inaccurate historical content","author":"Robertson Adi","year":"2024","unstructured":"Adi Robertson. 2024. Google AI\u2019s Gemini criticized for generating inaccurate historical content. https:\/\/www.theverge.com\/2024\/2\/21\/24079371\/google-ai-gemini-generative-inaccurate-historical Accessed: 2024-09-09."},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"crossref","unstructured":"Tobias Schnabel and Jennifer Neville. 2024. Prompts As Programs: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization. https:\/\/arxiv.org\/abs\/2309.00770","DOI":"10.18653\/v1\/2024.findings-emnlp.37"},{"key":"e_1_3_3_3_85_2","doi-asserted-by":"crossref","unstructured":"Patrick Schober Christa Boer and Lothar\u00a0A. Schwarte. 2018. Correlation Coefficients: Appropriate Use and Interpretation. Anesthesia & Analgesia5 (2018).","DOI":"10.1213\/ANE.0000000000002864"},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00211"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978392"},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"crossref","unstructured":"Taylor Shin Yasaman Razeghi Robert\u00a0L Logan\u00a0IV Eric Wallace and Sameer Singh. 2020. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts. https:\/\/arxiv.org\/abs\/2010.15980","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"e_1_3_3_3_89_2","unstructured":"Craig Smith. 2023. What Large Models Cost You - There Is No Free AI Lunch. Forbes (2023). https:\/\/www.forbes.com\/sites\/craigsmith\/2023\/09\/08\/what-large-models-cost-you\u2013there-is-no-free-ai-lunch\/?sh=1f3c5fa34af7"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.875"},{"key":"e_1_3_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642754"},{"key":"e_1_3_3_3_92_2","volume-title":"27th USENIX Security Symposium (USENIX Security 18)","author":"Suciu Octavian","year":"2018","unstructured":"Octavian Suciu, Radu Marginean, Yigitcan Kaya, Hal\u00a0Daume III, and Tudor Dumitras. 2018. When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks. In 27th USENIX Security Symposium (USENIX Security 18)."},{"key":"e_1_3_3_3_93_2","unstructured":"U.S. Census Bureau. 2020. Census Data. https:\/\/data.census.gov\/"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354212"},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2015.23035"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371855"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.23238"},{"key":"e_1_3_3_3_98_2","unstructured":"Laura Weidinger John Mellor Maribeth Rauh Conor Griffin Jonathan Uesato Po-Sen Huang Myra Cheng Mia Glaese Borja Balle Atoosa Kasirzadeh Zac Kenton Sasha Brown Will Hawkins Tom Stepleton Courtney Biles Abeba Birhane Julia Haas Laura Rimell Lisa\u00a0Anne Hendricks William Isaac Sean Legassick Geoffrey Irving and Iason Gabriel. 2021. Ethical and Social Risks of Harm from Language Models. https:\/\/arxiv.org\/abs\/2112.04359"},{"key":"e_1_3_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533088"},{"key":"e_1_3_3_3_100_2","doi-asserted-by":"publisher","unstructured":"K.\u00a0Maria Wolters Klaus-Peter Engelbrecht Florian G\u00f6dde Sebastian M\u00f6ller Anja Naumann and Robert Schleicher. 2010. Making it Easier for Older People to Talk to Smart Homes: the Effect of Early Help Prompts. Universal Access in the Information Society (2010). 10.1007\/s10209-009-0184-x","DOI":"10.1007\/s10209-009-0184-x"},{"key":"e_1_3_3_3_101_2","doi-asserted-by":"publisher","unstructured":"Qunfang Wu Yisi Sang Dakuo Wang and Zhicong Lu. 2023. Malicious Selling Strategies in Livestream E-commerce: A Case Study of Alibaba\u2019s Taobao and ByteDance\u2019s TikTok. ACM Trans. Comput.-Hum. Interact. (2023). 10.1145\/3577199","DOI":"10.1145\/3577199"},{"key":"e_1_3_3_3_102_2","unstructured":"Tongshuang Wu Michael Terry and Carrie\u00a0J. Cai. 2022. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. https:\/\/arxiv.org\/abs\/2110.01691"},{"key":"e_1_3_3_3_103_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu Xilie","year":"2024","unstructured":"Xilie Xu, Keyi Kong, Ning Liu, Lizhen Cui, Di Wang, Jingfeng Zhang, and Mohan Kankanhalli. 2024. An LLM can Fool Itself: A Prompt-Based Adversarial Attack. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_3_104_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445445"},{"key":"e_1_3_3_3_105_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.81"},{"key":"e_1_3_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.446"},{"key":"e_1_3_3_3_107_2","volume-title":"International Conference on Foundations of Digital Games","author":"Zagal Jos\u00e9\u00a0Pablo","year":"2013","unstructured":"Jos\u00e9\u00a0Pablo Zagal, Staffan Bj\u00f6rk, and Chris Lewis. 2013. Dark Patterns in the Design of Games. In International Conference on Foundations of Digital Games. https:\/\/api.semanticscholar.org\/CorpusID:17683705"},{"key":"e_1_3_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_3_109_2","unstructured":"Yifan Zeng Yiran Wu Xiao Zhang Huazheng Wang and Qingyun Wu. 2024. AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks. (2024)."},{"key":"e_1_3_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557347"},{"key":"e_1_3_3_3_111_2","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3620182"},{"key":"e_1_3_3_3_112_2","unstructured":"JJ Zhuang. 2023. Bringing Inspirational AI-Powered Search to the Instacart app with Ask Instacart. https:\/\/www.instacart.com\/company\/updates\/bringing-inspirational-ai-powered-search-to-the-instacart-app-with-ask-instacart\/ Accessed: 2024-06-05."},{"key":"e_1_3_3_3_113_2","unstructured":"Andy Zou Zifan Wang J.\u00a0Zico Kolter and Matt Fredrikson. 2023. Universal and Transferable Adversarial Attacks on Aligned Language Models. https:\/\/arxiv.org\/abs\/2307.15043"}],"event":{"name":"CHI 2025: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3714025","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3706598.3714025","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3714025","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3714025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T04:59:55Z","timestamp":1751605195000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3714025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":112,"alternative-id":["10.1145\/3706598.3714025","10.1145\/3706598"],"URL":"https:\/\/doi.org\/10.1145\/3706598.3714025","relation":{},"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2025-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}