Recent work has proposed stateful defense models (SDMs) as a compelling strategy to defend against a black-box attacker who only has query access to the model, as is common for online machine learning platforms. Such stateful defenses aim to defend against black-box attacks by tracking the query history and detecting and rejecting queries that are "similar" and thus preventing black-box attacks from finding useful gradients and making progress towards finding adversarial attacks within a reasonable query budget. Recent SDMs (e.g., Blacklight and PIHA) have shown remarkable success in defending against state-of-the-art black-box attacks. In this paper, we show that SDMs are highly vulnerable to a new class of adaptive black-box attacks. We propose a novel adaptive black-box attack strategy called Oracle-guided Adaptive Rejection Sampling (OARS) that involves two stages: (1) use initial query patterns to infer key properties about an SDM's defense; and, (2) leverage those extracted properties to design subsequent query patterns to evade the SDM's defense while making progress towards finding adversarial inputs. OARS is broadly applicable as an enhancement to existing black-box attacks - we show how to apply the strategy to enhance six common black-box attacks to be more effective against current class of SDMs. For example, OARS-enhanced versions of black-box attacks improved attack success rate against recent stateful defenses from almost 0% to to almost 100% for multiple datasets within reasonable query budgets.
SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
Jagiellonian University, Faculty of Mathematics and Computer Science（杰洛内维大学数学与计算机科学学院）；Jagiellonian University, Doctoral School of Exact and Natural Sciences（杰洛内维大学精确与自然科学研究博士学院）；Akces NCBR；IDEAS Research Institute（IDEAS研究所）
CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学与工程学院）；Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系）；Big Data Institute, Central South University（中南大学大数据研究院）
Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks
School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机学院）；Shanghai Key Laboratory of Integrated Administration Technologies for Information Security（上海市信息安全综合管理技术重点实验室）；Department of Computer Science, University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系）；School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（上海交通大学信息科学与工程学院）；Department of Machine Learning, Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学机器学习系）
AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning
Islamic University of Technology, Bangladesh（伊斯兰技术大学）；United International University, Bangladesh（联合国际大学）；University of Maryland, Baltimore County, MD, USA（马里兰大学巴尔的摩县分校）
Secure Confidential Business Information When Sharing Machine Learning Models
School of Management, Fudan University（复旦大学管理学院）；School of Management and Economics, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）经管学院）；Lerner College of Business and Economics, University of Delaware（特拉华大学勒纳商业与经济学院）
Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense
School of Cyber Science and Engineering, Southeast University, Purple Mountain Laboratories, and Jiangsu Province Engineering Research Center of Security for Ubiquitous Network（网络安全学院、东南大学、紫山实验室以及江苏省物联网安全工程技术研究中心）
Generalized DC loop current attack against the KLJN secure key exchange scheme
研究了一种新的对基尔霍夫定律-约翰逊噪声（Kirchhoff Law Johnson Noise，KLJN）安全密钥分发系统的攻击方法，该方法在Alices和Bobs两端引入未知的寄生直流电压源.本文是我们早期的调查与单端寄生源的推广。假设夏娃不知道的寄生源的值，一个新的攻击，利用寄生直流电压源产生的电流，介绍。该攻击是数学分析和演示的计算机模拟。简单的防御方法对攻击显示。早期的防御方法仅基于Alice和Bob的端子处的电流/电压数据的比较在这里是无用的，因为导线电流和电压在两端是相等的。然而，更昂贵的版本的早期防御方法，这是基于现场系统模拟和比较与测量，有效地工作。
SecureSplit: Mitigating Backdoor Attacks in Split Learning
Case Western Reserve University（凯斯西储大学）；Northeast Electric Power University（东北电力大学）；Fudan University（复旦大学）；University of Louisville（路易斯维尔大学）；University of North Texas（北德克萨斯大学）；The University of Queensland（昆士兰大学）；Swinburne University of Technology（斯威本科技大学）；City University of Hong Kong（香港城市大学）
Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
Institute of Artificial Intelligence (TeleAI), China Telecom, China（人工智能研究院（TeleAI），中国电信，中国）；Northwestern Polytechnical University（西北工业大学）；China Telecom, China（中国电信，中国）
