microsoft / CodeGenerationPoisoning
Proof of concept code for poisoning code generation models.
☆36Updated 9 months ago
Related projects: ⓘ
- Fault-aware neural code rankers☆23Updated last year
- A library for statistically estimating the privacy of ML pipelines from membership inference attacks☆31Updated 3 weeks ago
- Membership Inference Competition☆30Updated last year
- Universal Robustness Evaluation Toolkit (for Evasion)☆29Updated 6 months ago
- On Training Robust PDF Malware Classifiers (Usenix Security'20) https://arxiv.org/abs/1904.03542☆29Updated 2 years ago
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆55Updated 2 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆48Updated last week
- [ICLR 2021] "Generating Adversarial Computer Programs using Optimized Obfuscations" by Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shi…☆25Updated 2 years ago
- Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs (ACM CCS'21)☆17Updated last year
- Learning Security Classifiers with Verified Global Robustness Properties (CCS'21) https://arxiv.org/pdf/2105.11363.pdf☆25Updated 2 years ago
- Machine Learning & Security Seminar @Purdue University☆25Updated last year
- ☆16Updated last year
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publis…☆54Updated 10 months ago
- ☆87Updated 2 months ago
- ☆16Updated 2 years ago
- A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]☆87Updated last year
- ☆60Updated 3 years ago
- ☆111Updated 3 months ago
- This repository contains code and data of the paper **On the Limitations of Continual Learning for Malware Classification**, accepted to …☆14Updated 8 months ago
- Coverage-Guided Testing of Long Short-Term Memory (LSTM) Networks☆17Updated 3 years ago
- ☆42Updated last year
- This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Secur…☆11Updated 2 years ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆11Updated 3 weeks ago
- ☆17Updated 6 months ago
- ☆19Updated 3 years ago
- A repository to quickly generate synthetic data and associated trojaned deep learning models☆74Updated last year
- For our ICSE 2022 paper EAGLE: Creating Equivalent Graphs to Test Deep Learning Libraries☆12Updated last year
- Library for training globally-robust neural networks.☆28Updated last year
- ☆133Updated 4 months ago
- A Python library for Secure and Explainable Machine Learning☆144Updated 4 months ago