collaborators

6 papers

cs.CV2026

STEC: A Reference-Free Spatio-Temporal Entropy Coverage Metric for Evaluating Sampled Video Frames

Shih-Yao Lin

Frame sampling is a fundamental component in video understanding and video--language model pipelines, yet evaluating the quality of sampled frames remains challenging. Existing eva…

cs.CV2025

From Captions to Keyframes: KeyScore for Multimodal Frame Scoring and Video-Language Understanding

Shih-Yao Lin, Sibendu Paul, Caren Chen

Selecting informative keyframes is critical for efficient video understanding, yet existing approaches often rely on heuristics, ignore semantics, or produce redundant frames. We p…

cs.CR2025

Web Fraud Attacks Against LLM-Driven Multi-Agent Systems

Dezhang Kong, Hujin Peng, Yilun Zhang +5

With the proliferation of LLM-driven multi-agent systems (MAS), the security of Web links has become a critical concern. Once MAS is induced to trust a malicious link, attackers ca…

cs.CR2025

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Zonghao Ying, Siyang Wu, Run Hao +44

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…

cs.CL2025

Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs

Hongming Yang, Shi Lin, Jun Shao +4

Lightweight Large Language Models (LwLLMs) are reduced-parameter, optimized models designed to run efficiently on consumer-grade hardware, offering significant advantages in resour…

cs.CR2025

A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures

Dezhang Kong, Shi Lin, Zhenhua Xu +16

In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no…