9 papers
Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
Fazhong Liu, Zhuoyan Chen, Tu Lan +6
Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and…
Controlling Chat Style in Language Models via Single-Direction Editing
Zhenyu Xu, Victor S. Sheng
Controlling stylistic attributes in large language models (LLMs) remains challenging, with existing approaches relying on either prompt engineering or post-training alignment. This…
A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors
Zhenyu Xu, Victor S. Sheng
Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel finger…
CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models
Zhenyu Xu, Victor S. Sheng
The rise of large language models (LLMs) like ChatGPT has significantly improved automated code generation, enhancing software development efficiency. However, this introduces chal…
Multi-Task Program Error Repair and Explanatory Diagnosis
Zhenyu Xu, Victor S. Sheng
Program errors can occur in any type of programming, and can manifest in a variety of ways, such as unexpected output, crashes, or performance issues. And program error diagnosis c…
Logic Error Localization in Student Programming Assignments Using Pseudocode and Graph Neural Networks
Zhenyu Xu, Kun Zhang, Victor S. Sheng
Pseudocode is extensively used in introductory programming courses to instruct computer science students in algorithm design, utilizing natural language to define algorithmic behav…