Exploring the Adversarial Capabilities of Large Language Models
German Research Center for AI (DFKI)(德国人工智能研究中心);Technical University of Darmstadt(达姆施塔特工业大学);DataSpark GmbH(DataSpark有限公司);Centre for Cognitive Science of Darmstadt(达姆施塔特认知科学中心);Hessian Center for AI (hessian.AI)(黑森州人工智能中心)
Lukas Struppek, Minh Hieu Le, Dominik Hintersdorf, Kristian Kersting
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into the security and privacy issues of LLMs, the extent to which these models can exhibit adversarial behavior remains largely unexplored. Addressing this gap, we investigate whether common publicly available LLMs have inherent capabilities to perturb text samples to fool safety measures, so-called adversarial examples resp.~attacks. More specifically, we investigate whether LLMs are inherently able to craft adversarial examples out of benign samples to fool existing safe rails. Our experiments, which focus on hate speech detection, reveal that LLMs succeed in finding adversarial perturbations, effectively undermining hate speech detection systems. Our findings carry significant implications for (semi-)autonomous systems relying on LLMs, highlighting potential challenges in their interaction with existing systems and safety measures.
Exploring the Privacy Protection Capabilities of Chinese Large Language Models
School of Computer Science and Technology, Beijing Jiaotong University(北京交通大学计算机与信息技术学院);Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University(北京交通大学交通数据分析与挖掘北京市重点实验室);Key Laboratory of Big Data Artificial Intelligence in Transportation(Beijing Jiaotong University), Ministry of Education(交通大数据人工智能教育部重点实验室(北京交通大学))
CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges
Shanghai AI Laboratory(上海人工智能实验室);Wuhan University(武汉大学);Renmin University of China(中国人民大学);Beijing University of Posts and Telecommunications(北京邮电大学);Shanghai Jiao Tong University(上海交通大学)
Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
AI Thrust(AI 部);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Guangzhou HKUST Fok Ying Tung Research Institute(广州香港科技大学霍英东研究院);The Hong Kong University of Science and Technology(香港科技大学)
AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to How
University of Toronto(多伦多大学);Drexel University(德雷塞尔大学);University of Siegen(锡根大学);Westphal College of Media Arts and Design(媒体艺术与设计西弗尔学院);Digital Media Department(数字媒体系);Information Systems(信息系统)
Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization
TECNALIA, Basque Research and Technology Alliance (BRTA)(TECNALIA,巴斯克研究与技术联盟);University of the Basque Country (UPV/EHU)(巴斯克大学);University of Granada(格拉纳达大学);DaSCI Andalusian Institute of Data Science and Computational Intelligence(DaSCI安达卢西亚数据科学与计算智能研究所);Medical University of Graz(格拉茨医科大学);Alberta Machine Intelligence Institute(阿尔伯塔机器智能研究所);University of Alberta(阿尔伯塔大学)
Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks
School of Information and Communication Technology, Griffith University(格里菲斯大学信息与通信技术学院);School of Computer Science, University of Technology Sydney(悉尼科技大学计算机科学学院);College of Computer and Information Science, Southwest University(西南大学计算机与信息科学学院);School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间科学与工程学院)
Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surface
Center for Theoretical Physics, Sloane Physics Laboratory, Yale University(理论物理中心,斯洛恩物理实验室,耶鲁大学);III. Physics Institute A, RWTH Aachen University(物理研究所A,亚琛工业大学)
Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
Lomonosov Moscow State University(莫斯科罗蒙诺索夫国立大学);ISP RAS Research Center for Trusted Artificial Intelligence(俄罗斯科学院信息学与管理研究中心可信人工智能研究中心);MSU Institute for Artificial Intelligence(莫斯科国立大学人工智能研究所);Innopolis University(Innopolis大学)
Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs
School of Cyberspace, Hangzhou Dianzi University(杭州电子科技大学信息学院);Hangzhou Dianzi University(杭州电子科技大学);Beihang University(北京航空航天大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
State Key Laboratory of Complex & Critical Software Environment (CCSE), Beihang University(复杂与关键软件环境国家重点实验室,北京航空航天大学);Zhongguancun Laboratory(中关村实验室);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Department of Information Technology and Electrical Engineering, ETH Zurich(苏黎世联邦理工学院信息科技与电气工程系)
Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
Rochester Institute of Technology(罗切斯特技术研究所);University of Missouri - Kansas City(密苏里大学-凯撒城分校);U.S. Naval Research Laboratory(美国海军研究实验室);Lamar University(拉马尔大学);Meta AI;University of Rochester(罗切斯特大学);Rutgers University(新泽西罗格斯大学)
Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience
Sichuan University(四川大学);Chengdu University of Information Technology(成都信息工程大学);Shihezi University(石河子大学);Tianjin University(天津大学);Huazhong University of Science and Technology(华中科技大学)