datasec-lab / CodeBreaker
[USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
☆25Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for CodeBreaker
- ☆15Updated last month
- ☆96Updated 4 months ago
- The automated prompt injection framework for LLM-integrated applications.☆163Updated 2 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆94Updated last month
- ☆29Updated last month
- ☆23Updated 3 years ago
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…☆56Updated last month
- SecLLMHolmes is a generalized, fully automated, and scalable framework to systematically evaluate the performance (i.e., accuracy and rea…☆39Updated 2 weeks ago
- Machine Learning & Security Seminar @Purdue University☆25Updated last year
- ☆39Updated 9 months ago
- ☆13Updated 2 months ago
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publis…☆55Updated last year
- ☆18Updated 8 months ago
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆56Updated 2 years ago
- LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins☆25Updated 3 months ago
- ☆23Updated 2 months ago
- ☆16Updated 2 years ago
- ☆74Updated 7 months ago
- A curated list of academic events on AI Security & Privacy☆135Updated 3 months ago
- ☆11Updated last month
- Official repo for "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"☆13Updated 4 months ago
- Statistics of acceptance rate for the top conferences: Oakland, CCS, USENIX Security, NDSS.☆118Updated 3 weeks ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆66Updated this week
- This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses☆146Updated 2 months ago
- Code for paper "SrcMarker: Dual-Channel Source Code Watermarking via Scalable Code Transformations" (IEEE S&P 2024)☆21Updated 3 months ago
- A collection of security papers on top-tier publications☆36Updated this week
- Code to generate NeuralExecs (prompt injection for LLMs)☆17Updated 3 months ago
- Academic Papers about LLM Application on Security☆110Updated 5 months ago
- Official repository for CVPR'23 paper: Detecting Backdoors in Pre-trained Encoders☆30Updated last year