A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain protection, and MLOps pipeline security.

A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)

A curated list of academic events on AI Security & Privacy

APBench: A Unified Availability Poisoning Attack and Defenses Benchmark (TMLR 08/2024)

[ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

🤯 AI Security EXPOSED! Live Demos Showing Hidden Risks of 🤖 Agentic AI Flows: 💉Prompt Injection, ☣️ Data Poisoning. Watch the recorded session:

The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on poisoned dataset.

Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression

How Robust are Randomized Smoothing based Defenses to Data Poisoning? (CVPR 2021)

Experiments on Data Poisoning Regression Learning

MIT IEEE URTC 2023. GSET 2023. Repository for "SeBRUS: Mitigating Data Poisoning in Crowdsourced Datasets with Blockchain". Using Ethereum smart contracts to stop AI security attacks on crowdsourced datasets.

CCS'22 Paper: "Identifying a Training-Set Attack’s Target Using Renormalized Influence Estimation"

The first anti-AI tarpit. Rewritten in Python. Traps LLM crawlers in an infinite maze of fake pages and Markov babble.

Measure and Boost Backdoor Robustness

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning. (Neurips 2021)

A research framework for implementing and evaluating poisoning attacks on Retrieval-Augmented Generation (RAG) systems, enabling the study of their security vulnerabilities.

Code for the paper Analysis and Detectability of Offline Data Poisoning Attacks on Linear Systems.

fake prime [research sponsored by librandom S.C.H.]