CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Documenti analoghi

• Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
  di: Zhao, Jian, et al.
  Pubblicazione: (2024)
• Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
  di: Li, Yue, et al.
  Pubblicazione: (2026)
• Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
  di: Chang, Shuyu, et al.
  Pubblicazione: (2026)
• Similar but Patched Code Considered Harmful -- The Impact of Similar but Patched Code on Recurring Vulnerability Detection and How to Remove Them
  di: Tan, Zixuan, et al.
  Pubblicazione: (2024)
• Demonstration Attack against In-Context Learning for Code Intelligence
  di: Ge, Yifei, et al.
  Pubblicazione: (2024)