You see what I want you to see: poisoning vulnerabilities in neural code search
Abstract
Searching and reusing code snippets from open-source software repositories based on natural-language queries can greatly improve programming productivity.Recently, deep-learning-based approaches have become increasingly popular for code search. Despite substantial progress in training accurate models of code search, the robustness of these models has received little attention so far.
BibTeX
@inproceedings{Wan-al:FSE22,
author = {Yao Wan and
Shijie Zhang and
Hongyu Zhang and
Yulei Sui and
Guandong Xu and
Dezhong Yao and
Hai Jin and
Lichao Sun},
title = {You see what I want you to see: poisoning vulnerabilities in neural code search},
booktitle = {{ESEC/SIGSOFT} {FSE}},
pages = {1233--1245},
publisher = {{ACM}},
year = {2022},
}