activity
20222026
most citedAn LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

9 citations · 10 across the 9 of their papers we have counts for

collaborators
Showing 2023Show all

1 paper · 1 filter

cs.CR2023★ 1 cited

Poisoned ChatGPT Finds Work for Idle Hands: Exploring Developers' Coding Practices with Insecure Suggestions from Poisoned AI Models

Sanghak Oh, Kiho Lee, Seonhye Park +2

AI-powered coding assistant tools have revolutionized the software engineering ecosystem. However, prior work has demonstrated that these tools are vulnerable to poisoning attacks.…