8 papers
Malaika: Understanding Malware through Tri-Grounded Agentic Reasoning
Xingzhi Qian, Xinran Zheng, Yiling He +1
Recent LLM-based systems have shown promising capabilities for security-focused code analysis. Malware understanding, however, poses a distinct challenge: analysts must reconstruct…
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
Hongwei Yao, Yiming Liu, Yiling He +1
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond expl…
Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis
Yiling He, Junchi Lei, Hongyu She +5
Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve…
Esim: EVM Bytecode Similarity Detection Based on Stable-Semantic Graph
Zhuo Chen, Gaoqiang Ji, Yiling He +2
Decentralized finance (DeFi) is experiencing rapid expansion. However, prevalent code reuse and limited open-source contributions have introduced significant challenges to the bloc…
Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing
Xinran Zheng, Xingzhi Qian, Yiling He +2
Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them wi…
Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models
Xinran Zheng, Xingzhi Qian, Huichi Zhou +4
Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations. These issues, exacerbate…