3 papers
cs.CR2024
Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
Yuxi Li, Yi Liu, Yuekang Li +4
Large language models (LLMs) have revolutionized various applications, making robust safety alignment essential to prevent harmful outputs. Current safety alignment techniques, how…
cs.CR2024
Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
Md Imran Hossen, Sai Venkatesh Chilukoti, Liqun Shan +3
Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications ari…
cs.CL2023
ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
Xiangru Tang, Yuliang Liu, Zefan Cai +21
Despite Large Language Models (LLMs) like GPT-4 achieving impressive results in function-level code generation, they struggle with repository-scale code understanding (e.g., coming…