111 citations · 409 across the 43 of their papers we have counts for
15 papers · 1 filter
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Ruoqi Guo, Yi Liu, Gelei Deng +6
Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classi…
AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
Junchen Ding, Jialiang Dong, Yichen Zhu +5
The integration of Large Language Models (LLMs) into cybersecurity has transformed vulnerability assessment, but it has also produced a trustworthiness crisis driven by the uncheck…
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
Yue Wang, Yi Liu, Gelei Deng +4
Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution channel fo…
Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code
Zihao Xu, Yuekang Li, Gelei Deng +2
LLM-integrated applications blend natural language prompts with program code, and much of their runtime behavior originates in the prompt layer rather than in the code itself. Exis…
A Survey of LLM-Driven Penetration Testing: Taxonomy, Co-Evolution, and Open Challenges
Zheyuan He, Jiaxun Dong, Zihao Li +6
Agents4Pentest, an emerging class of LLM-based autonomous penetration testing systems, has become a rapidly growing area in security research. Despite this growth, the field still…
SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
Yubin Qu, Yi Liu, Gelei Deng +4
A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We cal…
MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
Ruoqi Guo, Yi Liu, Gelei Deng +7
Mobile graphical user interface (GUI) agents driven by vision-language models (VLMs) perceive the screen as rendered pixels and choose actions from what they see, so they cannot re…
Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
Yubin Qu, Ying Zhang, Yanjun Zhang +4
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated fil…
Membership Inference Attacks Against Video Large Language Models
Wei Song, Yuxin Cao, Ziqi Ding +3
Video large language models (VideoLLMs) are increasingly trained or instruction-tuned on large-scale video--text corpora collected from heterogeneous sources, raising an immediate…
Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
Yubin Qu, Yi Liu, Tongcheng Geng +5
LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages,…
How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
Zhihao Chen, Ying Zhang, Yi Liu +7
Large Language Model (LLM) agents increasingly rely on third-party skills that operate within privileged execution environments and routinely handle sensitive credentials, yet how…
What Makes a Good LLM Agent for Real-world Penetration Testing?
Gelei Deng, Yi Liu, Yuekang Li +5
LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28 LLM-based penetration testing…
"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
Yi Liu, Zhihao Chen, Yanjun Zhang +4
LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privile…
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Yi Liu, Weizhe Wang, Ruitao Feng +5
The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this arc…
Robust CAPTCHA Using Audio Illusions in the Era of Large Language Models: from Evaluation to Advances
Ziqi Ding, Yunfeng Wan, Wei Song +7
CAPTCHAs are widely used by websites to block bots and spam by presenting challenges that are easy for humans but difficult for automated programs to solve. To improve accessibilit…