Skip to content

Repository files navigation

Trojan Signatures in Code-LLMs

We investigate whether backdoored (trojaned) code large language models can be detected by inspecting their weights, a technique that has proven effective for vision models. Through extensive analysis of trojaned models on clone and defect detection tasks, we show that these weight-based “trojan signatures” largely fail to generalize to code LLMs, even under strong poisoning settings. Our findings highlight a critical security gap: modern code LLMs can hide backdoors without leaving clear parameter-level traces, making trojan detection significantly harder than previously assumed.

📄 Paper

Aftab Hussain, Md Rafiqul Islam Rabin, and Mohammad Amin Alipour. On Trojan Signatures in Large Language Models of Code. In International Conference on Learning Representations (ICLR) Workshop on Secure and Trustworthy Large Language Models (SeT LLM), Vienna, Austria, 2024.

👉 Read the paper here

About

Investigating lightweight approaches for trojan detection in code models using only model parameters.

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages