collaborators

7 papers

cs.CR2026

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…

cs.CR2026

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…

cs.AI2026

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…

cs.CV2025

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…

cs.LG2025

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…

cs.CV2025

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…