Publications (11)
When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?
Chong Chen, Jianzhong Su, Jiachi Chen +7
With the development of blockchain technology, smart contracts have become an important component of blockchain applications. Despite their crucial role, the development of smart c…
Knowledge-Enhanced Agentic Vulnerability Repair
Sicong Cao, Hao Ma, Le Yu +8
Frontier foundation models have changed the math on vulnerability discovery, but the bigger challenge is how the remediation side keeps up. Despite recent progresses in Automated V…
Hyperion: Unveiling DApp Inconsistencies using LLM and Dataflow-Guided Symbolic Execution
Shuo Yang, Xingwei Lin, Jiachi Chen +5
The rapid advancement of blockchain platforms has significantly accelerated the growth of decentralized applications (DApps). Similar to traditional applications, DApps integrate f…
Better Pay Attention Whilst Fuzzing
Shunkai Zhu, Jingyi Wang, Jun Sun +4
Fuzzing is one of the prevailing methods for vulnerability detection. However, even state-of-the-art fuzzing methods become ineffective after some period of time, i.e., the coverag…
MalGuard: Towards Real-Time, Accurate, and Actionable Detection of Malicious Packages in PyPI Ecosystem
Xingan Gao, Xiaobing Sun, Sicong Cao +5
Malicious package detection has become a critical task in ensuring the security and stability of the PyPI. Existing detection approaches have focused on advancing model selection,…
HODOR: Shrinking Attack Surface on Node.js via System Call Limitation
Wenya Wang, Xingwei Lin, Jingyi Wang +4
Node.js provides Node.js applications with system interaction capabilities using system calls. However, such convenience comes with a price, i.e., the attack surface of JavaScript…
SmartOracle: Generating Smart Contract Oracle via Fine-Grained Invariant Detection
Jianzhong Su, Jiachi Chen, Zhiyuan Fang +3
As decentralized applications (DApps) proliferate, the increased complexity and usage of smart contracts have heightened their susceptibility to security incidents and financial lo…
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Jiahao Yu, Xingwei Lin, Zheng Yu +1
Large language models (LLMs) have recently experienced tremendous popularity and are widely used from casual conversations to AI-driven programming. However, despite their consider…
DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
Wenhao Lin, Chenyu Yu, Xingwei Lin +6
As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states,…
MAS-SZZ: Multi-Agentic SZZ Algorithm for Vulnerability-Inducing Commit Identification
Sicong Cao, Jinxuan Xu, Le Yu +4
Accurate vulnerability-inducing commit identification serves as a foundation for a series of software security tasks, such as vulnerability detection and affected version analysis.…
ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack
Xingwei Lin, Wenhao Lin, Sicong Cao +4
Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively constructing adversarial contexts from…