Optimal Zero-Shot Detector for Multi-Armed Attacks
UMMISCO, IRD, Sorbonne Université(UMMISCO、法国发展研究院、索邦大学);New York University(纽约大学);Quebec AI Institute (MILA)(魁北克人工智能研究所(MILA))
Federica Granese, Marco Romanelli, Pablo Piantanida
备注:
Accepted to appear in the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), May 2nd - May 4th, 2024 This article supersedes arXiv:2302.02216
This paper explores a scenario in which a malicious actor employs a multi-armed attack strategy to manipulate data samples, offering them various avenues to introduce noise into the dataset. Our central objective is to protect the data by detecting any alterations to the input. We approach this defensive strategy with utmost caution, operating in an environment where the defender possesses significantly less information compared to the attacker. Specifically, the defender is unable to utilize any data samples for training a defense model or verifying the integrity of the channel. Instead, the defender relies exclusively on a set of pre-existing detectors readily available "off the shelf". To tackle this challenge, we derive an innovative information-theoretic defense approach that optimally aggregates the decisions made by these detectors, eliminating the need for any training data. We further explore a practical use-case scenario for empirical evaluation, where the attacker possesses a pre-trained classifier and launches well-known adversarial attacks against it. Our experiments highlight the effectiveness of our proposed solution, even in scenarios that deviate from the optimal setup.
Adversarial Attacks on Cooperative Multi-agent Bandits
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);East China Normal University(华东师范大学);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学);Southeast University(东南大学)
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
Zhejiang University(浙江大学);Nanyang Technological University(南洋理工大学);Sun Yat-sen University(中山大学);University of Science and Technology of China(中国科学技术大学);Virginia Tech(弗吉尼亚理工大学)
FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)
FBID: Adaptive Personalized Federated Learning for Robust Out-of-Distribution Attack Detection in IoT Networks
UTS-HCMUT JTIRC;Ho Chi Minh City University of Technology (HCMUT)(胡志明市技术大学(HCMUT));Vietnam National University Ho Chi Minh City (VNU-HCM)(越南国家大学胡志明市分校(VNU-HCM));University of Technology Sydney(悉尼科技大学)
Adversarial Attacks on Combinatorial Multi-Armed Bandits
Oregon State University(俄勒冈州立大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Pennsylvania State University(宾夕法尼亚州立大学);Princeton University(普林斯顿大学)
Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents
School of Computer Science, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center, Tsinghua University(清华大学计算机科学与技术系、人工智能研究院、清华-博世机器学习联合中心、清华脑与智能实验室、北京国家信息科学与技术研究中心)
MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks
Tsinghua University(清华大学);Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心(BNRist));JD AI Research(京东人工智能研究院);Shanghai University(上海大学)
Cyber-Physical Security and Safety of Autonomous Connected Vehicles: Optimal Control Meets Multi-Armed Bandit Learning
Centre for Wireless Communications (CWC), University of Oulu, Finland(奥卢大学无线通信中心(CWC));WINLAB, Dept. of ECE, Rutgers University, New Brunswick, NJ, USA(罗格斯大学WINLAB,电子与计算机工程系,新泽西州新布朗斯维尔,美国)
Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
Department of Electronics Engineering, Tsinghua University, Beijing, China(清华大学电子工程系);College of AI, Tsinghua University, Beijing, China(清华大学人工智能学院);Beijing National Research Center for Information Science and Technology, Beijing, China(北京信息科学国家研究中心)
Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines
Department of Computer Science, University of Texas at El Paso(德克萨斯理工大学计算机科学系);School of Computing, Southern Illinois University Carbondale(南方伊利诺伊大学卡本代尔分校计算机学院);Hanyang University(翰阳大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
A Grassmannian Approach to Zero-Shot Learning for Network Intrusion Detection
Institute of Systems and Robotics (ISR)(系统与机器人研究所);University of Coimbra(科英布拉大学);CISUC, Department of Informatics Engineering, University of Coimbra(科英布拉大学信息工程系CISUC);College of Computer Science and Technology, Henan Polytechnic University(河南理工大学计算机科学与技术学院);Department of Mathematics(数学系)
网络入侵检测中的一个主要问题是新攻击的不断增加,使得没有足够的标记样本来识别新的攻击类型。传统的机器学习方法很难解决这样的问题。这可以通过零样本学习来克服,这是计算机视觉领域的一种新方法,可以分为两个阶段:属性学习和推理阶段。提出了一种新的网络入侵检测推理阶段算法。为了实现这一目标,我们首先提出了一个实验装置,用于评估网络入侵检测相关任务中的零样本学习。其次,在AL阶段应用基于决策树的算法提取用于生成属性的规则。最后,使用Zero-Shot类的表示作为格拉斯曼流形中的点,该流形中的点之间的最短距离的显式公式可以用于计算表示新攻击的Zero-Shot类与对应于攻击类别的已知类之间的测地线距离。在KDD Cup 99和NSL-KDD数据集上的实验结果表明,我们的方法与零样本学习成功地解决了网络入侵检测问题。
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
School of Electronic Engineering(电子工程学院);Beijing University of Posts and Telecommunications(北京邮电大学);Centre for Frontier AI Research (CFAR)(前沿人工智能研究中心);Institute of High Performance Computing (IHPC)(高性能计算研究所);Agency for Science Technology and Research (A*STAR)(新加坡科技研究局);School of Information and Communication(信息与通信学院)