5 papers
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time
Yifan Lan, Yuanpu Cao, Weitong Zhang +2
Recently, Multimodal Large Language Models (MLLMs) have gained significant attention across various domains. However, their widespread adoption has also raised serious safety conce…
CyGATE: Game-Theoretic Cyber Attack-Defense Engine for Patch Strategy Optimization
Yuning Jiang, Nay Oo, Qiaoran Meng +5
Modern cyber attacks unfold through multiple stages, requiring defenders to dynamically prioritize mitigations under uncertainty. While game-theoretic models capture attacker-defen…
Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
Jiaxi Yang, Mengqi Zhang, Yiqiao Jin +8
Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence. However, the topology of th…
GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors
Yaopei Zeng, Yuanpu Cao, Lu Lin
The growing accessibility of diffusion models has revolutionized image editing but also raised significant concerns about unauthorized modifications, such as misinformation and pla…
Understanding and Rectifying Safety Perception Distortion in VLMs
Xiaohan Zou, Jian Kang, George Kesidis +1
Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater…