7 papers
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Puyu Zeng, Simeng Qin, Jingzhi Li +3
Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly ins…
Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
Ziwei Wang, Jing Chen, Ruichao Liang +6
Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive t…
RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection
Ziwei Wang, Yuanhe Zhang, Jing Chen +6
Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consu…
Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection
Jiabao Guo, Yadian Wang, Hui Ma +7
Real-world face recognition systems are vulnerable to both physical presentation attacks (PAs) and digital forgery attacks (DFs). We aim to achieve comprehensive protection of biom…
Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
Kunhao Li, Wenhao Li, Di Wu +4
Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity…
Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
Tuo Chen, Jie Gui, Minjing Dong +3
Self-supervised contrastive learning (CL) effectively learns transferable representations from unlabeled data containing images or image-text pairs but suffers vulnerability to dat…