4 citations · 14 across the 12 of their papers we have counts for
12 papers
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Xiaojun Jia, Jie Liao, Simeng Qin +5
Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely o…
Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines
Yifei Ge, Weisong Sun, Jinkun Xiao +8
Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, and the underlying system. For…
Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
Ziwei Wang, Jing Chen, Ruichao Liang +6
Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive t…
Sealing the Audit-Runtime Gap for LLM Skills
Tingda Shen, Yebo Feng, Konglin Zhu +3
Large language model (LLM) ecosystems such as Claude Code and ChatGPT increasingly rely on skills: packages of natural-language instructions and executable tools. Once in the LLM's…
A Visionary Look at Vibe Researching
Yebo Feng, Yang Liu
Vibe researching is an emerging paradigm in which human researchers provide high-level direction and critical judgment while LLM-based agents handle the labor-intensive execution o…
A Vision for Auto Research with LLM Agents
Chengwei Liu, Chong Wang, Jiayue Cao +16
This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Levera…
Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories
Alperen Yildiz, Sin G. Teo, Yiling Lou +3
Large Language Models (LLMs) have shown promise in software vulnerability detection, particularly on function-level benchmarks like Devign and BigVul. However, real-world detection…
Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization
Weisong Sun, Yiran Zhang, Jie Zhu +8
Commenting code is a crucial activity in software development, as it aids in facilitating future maintenance and updates. To enhance the efficiency of writing comments and reduce d…
Eliminating Backdoors in Neural Code Models for Secure Code Understanding
Weisong Sun, Yuchen Chen, Chunrong Fang +7
Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. However, numerous recent studies reveal that such models are…
LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion
Chong Wang, Kaifeng Huang, Jian Zhang +4
Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have shown effectiveness in generating code completions. However, in LLM-based code completion, LLMs…
Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?
TIngxu Han, Wei Song, Weisong Sun +7
Self-Supervised Learning (SSL) has become a prominent paradigm for pre-training encoders to learning general-purpose representations from unlabeled data and releasing them on third…
Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
Chong Wang, Jian Zhang, Yebo Feng +4
Code large language models (LLMs) face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies (e.g., user-defined attribute…