2.7k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Chinese Academy of SciencesCN296 papers
- University of Chinese Academy of SciencesCN142 papers
- State Key Laboratory of Information Security44 papers
- Beihang UniversityCN26 papers
- Tsinghua UniversityCN19 papers
- Institute of Computing TechnologyCN15 papers
- Sun Yat-sen UniversityCN13 papers
- Peking UniversityCN11 papers
- Alibaba Group (China)CN10 papers
- Renmin University of ChinaCN10 papers
- Nanyang Technological UniversitySG9 papers
- Peng Cheng LaboratoryCN8 papers
7 papers · 2 filters
FATS: A Prompt Injection Attack Utilizing Feign Security Agents with Deceptive Few-shots Learning
Yupeng Ren, Jiangtao Chen, Rui Zhang
Large Language Models (LLMs) face significant security risks despite their advanced capabilities. While techniques like Reinforcement Learning with Human Feedback (RLHF) improve et…
The Midas Touch: Triggering the Capability of LLMs for RM-API Misuse Detection
Yi Yang, Jinghua Liu, Kai Chen +1
In this paper, we propose an LLM-empowered RM-API misuse detection solution, ChatDetector, which fully automates LLMs for documentation understanding which helps RM-API constraints…
Generating API Parameter Security Rules with LLM for API Misuse Detection
Jinghua Liu, Yi Yang, Kai Chen +1
In this paper, we present a new framework, named GPTAid, for automatic APSRs generation by analyzing API source code with LLM and detecting API misuse caused by incorrect parameter…
DLP: towards active defense against backdoor attacks with decoupled learning process
Zonghao Ying, Bin Wu
Deep learning models are well known to be susceptible to backdoor attack, where the attacker only needs to provide a tampered dataset on which the triggers are injected. Models tra…
NBA: defensive distillation for backdoor removal via neural behavior alignment
Zonghao Ying, Bin Wu
Recently, deep neural networks have been shown to be vulnerable to backdoor attacks. A backdoor is inserted into neural networks via this attack paradigm, thus compromising the int…
Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
Hao Wang, Shangwei Guo, Jialing He +3
Pre-trained models (PTMs) are widely adopted across various downstream tasks in the machine learning supply chain. Adopting untrustworthy PTMs introduces significant security risks…
A Survey of Protocol Fuzzing
Xiaohan Zhang, Cen Zhang, Xinghua Li +8
Communication protocols form the bedrock of our interconnected world, yet vulnerabilities within their implementations pose significant security threats. Recent developments have s…