microsoft / CodeGenerationPoisoningLinks
Proof of concept code for poisoning code generation models.
☆55Updated 2 years ago
Alternatives and similar repositories for CodeGenerationPoisoning
Users that are interested in CodeGenerationPoisoning are comparing it to the libraries listed below
Sorting:
- ☆127Updated last year
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆56Updated 10 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆79Updated 5 months ago
- A curated list of academic events on AI Security & Privacy☆167Updated last year
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publis…☆84Updated 2 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆425Updated this week
- Universal Robustness Evaluation Toolkit (for Evasion)☆32Updated 4 months ago
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆60Updated 3 years ago
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…☆108Updated 3 weeks ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆83Updated 6 months ago
- ☆151Updated last year
- 🔮Reasoning for Safer Code Generation; 🥇Winner Solution of Amazon Nova AI Challenge 2025☆35Updated 5 months ago
- A repository to quickly generate synthetic data and associated trojaned deep learning models☆84Updated 2 years ago
- ☆55Updated last year
- Machine Learning & Security Seminar @Purdue University☆25Updated 2 years ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆103Updated last year
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆64Updated 2 months ago
- Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs (ACM CCS'21)☆17Updated 3 years ago
- ☆19Updated last year
- ☆85Updated last week
- Code for the AAAI 2023 paper "CodeAttack: Code-based Adversarial Attacks for Pre-Trained Programming Language Models☆34Updated 2 years ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- The automated prompt injection framework for LLM-integrated applications.☆251Updated last year
- ☆68Updated 5 years ago
- Learning Security Classifiers with Verified Global Robustness Properties (CCS'21) https://arxiv.org/pdf/2105.11363.pdf☆28Updated 4 years ago
- ☆78Updated last year
- A Python library for Secure and Explainable Machine Learning☆190Updated 7 months ago
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆103Updated last year
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Updated 4 months ago
- A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]☆90Updated 2 years ago