Data-oriented attacks manipulate non-control data to alter a program's benign behavior without violating its control-flow integrity. It has been shown that such attacks can cause significant damage even in the presence of control-flow defense mechanisms. However, these threats have not been adequately addressed. In this SoK paper, we first map data-oriented exploits, including Data-Oriented Programming (DOP) attacks, to their assumptions/requirements and attack capabilities. We also compare known defenses against these attacks, in terms of approach, detection capabilities, overhead, and compatibility. Then, we experimentally assess the feasibility of a detection approach that is based on the Intel Processor Trace (PT) technology. PT only traces control flows, thus, is generally believed to be not useful for data-oriented security. However, our work reveals that data-oriented attacks (in particular the recent DOP attacks) may generate side-effects on control-flow behavior in multiple dimensions, which manifest in PT traces. Based on this evaluation, we discuss challenges for building deployable data-oriented defenses and open research questions.
Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks
The Hong Kong University of Science and Technology（香港科技大学）；Zhejiang University of Technology（浙江工业大学）；Lingnan University（岭南大学）；School of Cyber Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；ZTE Corporation（中兴通讯有限公司）
PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
Modern mission-critical systems (MCS) are increasingly softwarized and interconnected. As a result, their complexity increased, and so their vulnerability against cyber-attacks. The current adoption of virtualization and service-oriented architectures (SOA) in MCSs provides additional flexibility that can be leveraged to withstand and mitigate attacks, e.g., by moving critical services or data flows. This enables the deployment of strategies for moving target defense (MTD), which allows stripping attackers of their asymmetric advantage from the long reconnaissance of MCSs. However, it is chall…
Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models
University of Wisconsin - Madison（威斯康星大学麦迪逊分校）；Hampton College（汉普顿学院）；Texas A&M University（德克萨斯农工大学）；Liberty University（自由大学）；Arizona State University（亚利桑那州立大学）
Since the discovery of adversarial attacks against machine learning models nearly a decade ago, research on adversarial machine learning has rapidly evolved into an eternal war between defenders, who seek to increase the robustness of ML models against adversarial attacks, and adversaries, who seek to develop better attacks capable of weakening or defeating these defenses. This domain, however, has found little buy-in from ML practitioners, who are neither overtly concerned about these attacks affecting their systems in the real world nor are willing to trade off the accuracy of their models i…
Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Georgia Institute of Technology（佐治亚理工学院）；Stanford University（斯坦福大学）；Amazon GenAI（亚马逊生成式人工智能部门）
University of Murcia（穆尔西亚大学）；armasuisse Science & Technology（瑞士国防采购与技术局科学与技术部）；University of Zurich（苏黎世大学）
In the last years, the number of IoT devices deployed has suffered an undoubted explosion, reaching the scale of billions. However, some new cybersecurity issues have appeared together with this development. Some of these issues are the deployment of unauthorized devices, malicious code modification, malware deployment, or vulnerability exploitation. This fact has motivated the requirement for new device identification mechanisms based on behavior monitoring. Besides, these solutions have recently leveraged Machine and Deep Learning techniques due to the advances in this field and the increase…
Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
Hangzhou Normal University（杭州师范大学）；Zhejiang University（浙江大学）；China Mobile (Zhejiang) Innovation Research Institute Co., Ltd.（中国移动（浙江）创新研究院有限公司）；Quantum Cloud Computing and Distributed Systems (qCLOUDS) Lab, School of Computing and Information Systems（量子云计算与分布式系统（qCLOUDS）实验室，计算与信息学院）；The University of Melbourne（墨尔本大学）
East China Normal University（东华大学）；Shanghai Innovation Institute（上海创新研究院）；University of Southampton（南安普顿大学）；Shanghai Jiao Tong University（上海交通大学）；Software Engineering Institute, East China Normal University（东华大学软件工程研究院）
