AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs

Chua Jin Chou, Sarang Nambiar, Murali Srinivasan +1

We present AKRASIA, a stealthy, inference-time backdoor attack against reasoning-based Code LLMs. AKRASIA aims to achieve a backdoor target (e.g., malicious code execution) in reas…