5 papers
How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment
Rui Zhu, Weiheng Bai, Qiushi Wu +3
Reinforcement Learning (RL) has emerged as a crucial paradigm for unlocking the advanced reasoning capabilities of Large Language Models (LLMs), encompassing frameworks like RLHF a…
GenDetect: Generalizing Reactive Detection for Resilience Against Imitative DeFi Attack Cascade
Bowen Cai, Weiheng Bai, Youshui Lu +4
As blockchain ecosystems grow, financially motivated attackers increasingly exploit decentralized finance (DeFi) protocols, causing frequent and severe losses. Unlike conventional…
Capturing Monetarily Exploitable Vulnerability in Smart Contracts via Auditor Knowledge-Learning Fuzzing
Bowen Cai, Weiheng Bai, Hangyun Tang +2
Smart contracts extended blockchain functionality beyond simple transactions, powering complex applications like decentralized finance (DeFi). However, this complexity introduces s…
Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities
Nanzi Yang, Weiheng Bai, Kangjie Lu
The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data sources. By defining a set of comm…
AFLGopher: Accelerating Directed Fuzzing via Feasibility-Aware Guidance
Weiheng Bai, Kefu Wu, Qiushi Wu +1
Directed fuzzing is a useful testing technique that aims to efficiently reach target code sites in a program. The core of directed fuzzing is the guiding mechanism that directs the…