From the 1 of 11 linked papers with an AI index.
11 papers
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
Haowen Dai, Zonghao Ying, Wenfeng Li +10
Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective c…
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Tianyuan Zhang, Zonglei Jing, Jiangfan Liu +47
The paper reports on the CVPR 2026@AdvML Workshop Challenge, which evaluated adversarial attacks on multimodal vision‑language agents for autonomous driving using multi‑view visual…
PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
Quanchen Zou, Zonghao Ying, Moyang Chen +7
The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation…
Improving Safety Alignment via Balanced Direct Preference Optimization
Shiji Zhao, Mengyang Wang, Shukun Xiong +7
With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from…
Evolving Deception: When Agents Evolve, Deception Wins
Zonghao Ying, Haowen Dai, Tianyuan Zhang +6
Self-evolving agents offer a promising path toward scalable autonomy. However, in this work, we show that in competitive environments, self-evolution can instead give rise to a ser…
Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
Quanchen Zou, Moyang Chen, Zonghao Ying +6
Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input r…