9 papers
SoK: Taxonomizing the Low-Level Attack Surface of Modern Web Browsers
Han Zheng, Qinying Wang, Qiang Liu +1
The web browser remains one of the most exposed remote attack surfaces on end-user systems, and memory-corruption flaws continue to play a central role in real-world browser exploi…
AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library
Minwei Kong, Ao Qu, Xiaotong Guo +12
Optimization modeling underlies critical decision-making across industries, yet remains difficult to automate: natural-language problem descriptions must be translated into precise…
Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
Jiaqi Weng, Han Zheng, Hanyu Zhang +6
Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive mos…
Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
Yunyi Zhang, Shibo Cui, Baojun Liu +4
LLM applications (i.e., LLM apps) leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional application development. While t…
Cuckoo Attack: Stealthy and Persistent Attacks Against AI-IDE
Xinpeng Liu, Junming Liu, Peiyu Liu +5
Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autono…
SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems
Peiran Li, Xinkai Zou, Zhuohang Wu +9
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Des…