27 citations · 85 across the 22 of their papers we have counts for
14 papers · 1 filter
MATRIX: Multi-Layer Code Watermarking via Dual-Channel Constrained Parity-Check Encoding
Yuqing Nie, Chong Wang, Guosheng Xu +4
Code Large Language Models (Code LLMs) have revolutionized software development but raised critical concerns regarding code provenance, copyright protection, and security. Existing…
Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
Shuai Yuan, Zhibo Zhang, Yuxi Li +2
The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform bas…
Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics
Shide Zhou, Kailong Wang, Ling Shi +1
The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threat…
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Yuxi Li, Zhibo Zhang, Kailong Wang +2
Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly ja…
Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
Yuqing Nie, Chong Wang, Kailong Wang +3
Code Large Language Models (LLMs) have demonstrated remarkable capabilities in generating, understanding, and manipulating programming code. However, their training process inadver…
Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
Jian Zhao, Shenao Wang, Yanjie Zhao +6
The proliferation of pre-trained models (PTMs) and datasets has led to the emergence of centralized model hubs like Hugging Face, which facilitate collaborative development and reu…
Towards Robust Detection of Open Source Software Supply Chain Poisoning Attacks in Industry Environments
Xinyi Zheng, Chen Wei, Shenao Wang +5
The exponential growth of open-source package ecosystems, particularly NPM and PyPI, has led to an alarming increase in software supply chain poisoning attacks. Existing static ana…
WALLETRADAR: Towards Automating the Detection of Vulnerabilities in Browser-based Cryptocurrency Wallets
Pengcheng Xia, Yanhui Guo, Zhaowen Lin +8
Cryptocurrency wallets, acting as fundamental infrastructure to the blockchain ecosystem, have seen significant user growth, particularly among browser-based wallets (i.e., browser…
Large Language Models for Cyber Security: A Systematic Literature Review
Hanxiang Xu, Shenao Wang, Ningke Li +6
The rapid advancement of Large Language Models (LLMs) has opened up new opportunities for leveraging artificial intelligence in a variety of application domains, including cybersec…
Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectors
Baijun Cheng, Shengming Zhao, Kailong Wang +6
Vulnerability detectors based on deep learning (DL) models have proven their effectiveness in recent years. However, the shroud of opacity surrounding the decision-making process o…
MalModel: Hiding Malicious Payload in Mobile Deep Learning Models with Black-box Backdoor Attack
Jiayi Hua, Kailong Wang, Meizhen Wang +3
Mobile malware has become one of the most critical security threats in the era of ubiquitous mobile computing. Despite the intensive efforts from security experts to counteract it,…
The Devil Behind the Mirror: Tracking the Campaigns of Cryptocurrency Abuses on the Dark Web
Pengcheng Xia, Zhou Yu, Kailong Wang +6
The dark web has emerged as the state-of-the-art solution for enhanced anonymity. Just like a double-edged sword, it also inadvertently becomes the safety net and breeding ground f…
MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis
Shenao Wang, Yuekang Li, Kailong Wang +4
The advent of MiniApps, operating within larger SuperApps, has revolutionized user experiences by offering a wide range of services without the need for individual app downloads. H…
Digger: Detecting Copyright Content Mis-usage in Large Language Model Training
Haodong Li, Gelei Deng, Yi Liu +7
Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed…