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

Shenao Yan, Shen Wang, Yue Duan, Hanbin Hong, Kiho Lee, Doowon Kim, Yuan Hong. An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection. In Davide Balzarotti, Wenyuan Xu 0001, editors, 33rd USENIX Security Symposium, USENIX Security 2024, Philadelphia, PA, USA, August 14-16, 2024. USENIX Association, 2024. [doi]

@inproceedings{YanWDHLKH24,
  title = {An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection},
  author = {Shenao Yan and Shen Wang and Yue Duan and Hanbin Hong and Kiho Lee and Doowon Kim and Yuan Hong},
  year = {2024},
  url = {https://www.usenix.org/conference/usenixsecurity24/presentation/yan},
  researchr = {https://researchr.org/publication/YanWDHLKH24},
  cites = {0},
  citedby = {0},
  booktitle = {33rd USENIX Security Symposium, USENIX Security 2024, Philadelphia, PA, USA, August 14-16, 2024},
  editor = {Davide Balzarotti and Wenyuan Xu 0001},
  publisher = {USENIX Association},
}