Login / Signup
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
Published in:
USENIX Security Symposium (2024)
Keyphrases
</>
automatic detection
probabilistic model
experimental data
detection accuracy
model selection
detection method
false alarms
data mining
prior knowledge
source code
anomaly detection
parameter estimation
detection rate