logo
Loading...
An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

Computer Science

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

S. Yan, S. Wang, et al.

Large Language Models now power smarter code completion—but what if they can be turned against us? CODEBREAKER introduces an LLM-assisted backdoor attack that stealthily transforms malicious payloads so poisoned fine-tuning data and generated code can evade strong detectors. This research was conducted by Shenao Yan, Shen Wang, Yue Duan, Hanbin Hong, Kiho Lee, Doowon Kim, and Yuan Hong.... show more
Citation Metrics
Citations
9
Influential Citations
3
Reference Count
97
Citation by Year

Note: The citation metrics presented here have been sourced from Semantic Scholar and OpenAlex.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny