4 papers
Experimental Settings in LLM-Based Program Repair: A Study of Inputs, Tool Access, Feedback, and Validation
Xushu Dai, Yicheng Cai, Nanqing Luo +1
Evaluations of automated program repair (APR) systems commonly report the benchmark, the number of repaired defects, and the tests used for final patch validation, but these items…
Detecting Avalanche Effect in Adversarial Settings: Spotting the Encryption Loops in Ransomware
Nanqing Luo, Xusheng Li, Haizhou Wang +3
Spotting encryption loops in binary-only ransomware is a critical reverse engineering task. Since the existence of avalanche effect, an intrinsic characteristic of any secure encry…
Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM
Haizhou Wang, Nanqing Luo, Xusheng Li +1
Sandboxes and other dynamic analysis processes are prevalent in malware detection systems nowadays to enhance the capability of detecting 0-day malware. Therefore, techniques of an…
Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles
Zhilong Wang, Haizhou Wang, Nanqing Luo +4
Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. B…