microsoft / CodeGenerationPoisoningLinks
Proof of concept code for poisoning code generation models.
☆50Updated last year
Alternatives and similar repositories for CodeGenerationPoisoning
Users that are interested in CodeGenerationPoisoning are comparing it to the libraries listed below
Sorting:
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆251Updated 3 weeks ago
- ☆121Updated last year
- A repository to quickly generate synthetic data and associated trojaned deep learning models☆80Updated 2 years ago
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆59Updated 3 years ago
- A curated list of academic events on AI Security & Privacy☆160Updated last year
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publis…☆75Updated last year
- Universal Robustness Evaluation Toolkit (for Evasion)☆31Updated 3 months ago
- ☆147Updated 10 months ago
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆100Updated last year
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆50Updated 5 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆64Updated 3 weeks ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆114Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆78Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆66Updated last month
- PhD/MSc course on Machine Learning Security (Univ. Cagliari)☆211Updated 3 months ago
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on …☆56Updated last month
- A library for statistically estimating the privacy of ML pipelines from membership inference attacks☆35Updated 2 weeks ago
- A Python library for Secure and Explainable Machine Learning☆185Updated 2 months ago
- ☆19Updated 4 years ago
- On Training Robust PDF Malware Classifiers (Usenix Security'20) https://arxiv.org/abs/1904.03542☆30Updated 3 years ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆40Updated 3 weeks ago
- This repository provides a benchmark for prompt Injection attacks and defenses☆267Updated last month
- The automated prompt injection framework for LLM-integrated applications.☆226Updated 11 months ago
- Fault-aware neural code rankers☆29Updated 2 years ago
- MAB-Malware an open-source reinforcement learning framework to generate AEs for PE malware. We model this problem as a classic multi-arme…☆49Updated 4 months ago
- 🔮Reasoning for Safer Code Generation; 🥇Winner Solution of Amazon Nova AI Challenge 2025☆22Updated last week
- ☆48Updated 11 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆54Updated last year
- ☆66Updated 4 years ago
- Code release for RobOT (ICSE'21)☆15Updated 2 years ago