5 papers
HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines
Kang Yang, Yunhang Zhang, Zichuan Li +3
Large language model (LLM)-based techniques have achieved notable progress in generating harnesses for program fuzzing. However, applying them to arbitrary functions (especially in…
Blackbox Dataset Inference for LLM
Ruikai Zhou, Kang Yang, Xun Chen +3
Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of d…
Rethinking the Evaluation of Secure Code Generation
Shih-Chieh Dai, Jun Xu, Guanhong Tao
Large language models (LLMs) are widely used in software development. However, the code generated by LLMs often contains vulnerabilities. Several secure code generation methods hav…
Alleviating the Fear of Losing Alignment in LLM Fine-tuning
Kang Yang, Guanhong Tao, Xun Chen +1
Large language models (LLMs) have demonstrated revolutionary capabilities in understanding complex contexts and performing a wide range of tasks. However, LLMs can also answer ques…
Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage
Soumil Datta, Shih-Chieh Dai, Leo Yu +1
Text-to-image diffusion models, such as Stable Diffusion, have shown exceptional potential in generating high-quality images. However, recent studies highlight concerns over the us…