Sensente/Security-Attacks-on-LCCTs
Security Attacks on LLM-based Code Completion Tools (AAAI 2025)
This project helps security researchers understand and demonstrate vulnerabilities in AI-powered code completion tools like GitHub Copilot and Amazon Q. By crafting specific code inputs, researchers can uncover ways these tools might generate unwanted or harmful code (jailbreaking) or accidentally expose sensitive training data. It's designed for cybersecurity professionals and AI safety researchers who analyze and audit large language models used in software development.
Use this if you are a security researcher or auditor investigating the robustness and potential risks of AI-driven code completion tools and want to replicate or develop new attack methodologies.
Not ideal if you are a software developer looking for tools to write more secure code or a user seeking to fix vulnerabilities in your own applications.
Stars
21
Forks
5
Language
Python
License
—
Category
Last pushed
Dec 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Sensente/Security-Attacks-on-LCCTs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gunthercox/chatterbot-corpus
A multilingual dialog corpus
EdinburghNLP/awesome-hallucination-detection
List of papers on hallucination detection in LLMs.
jfainberg/self_dialogue_corpus
The Self-dialogue Corpus - a collection of self-dialogues across music, movies and sports
jkkummerfeld/irc-disentanglement
Dataset and model for disentangling chat on IRC
Tomiinek/MultiWOZ_Evaluation
Unified MultiWOZ evaluation scripts for the context-to-response task.