Entry
Appears in 4 awesome lists
🟢 — Flagship machine-learning security library for evaluating and defending models against evasion, poisoning, extraction, and inference attacks across major ML frameworks. (LF AI & Data / IBM) · updated 2025-11-13); Related: Foolbox · PrivacyRaven
Section: AI/ML Supply Chain & Model Security · 🟢 — Flagship machine-learning security library for evaluating and defending models against evasion, poisoning, extraction, and inference attacks across major ML frameworks. (LF AI & Data / IBM) · updated 2025-11-13); Related: Foolbox · PrivacyRaven
Section: LLM Security & AI Security · Python library for adversarial machine learning.
Section: Privacy and Safety · ART (Adversarial Robustness Toolbox) provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference.
Section: Security Tools · Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
Visualizer for deep learning and machine learning models (no Python code, but visualizes models from most Python Deep Learning frameworks).
Curated list of tools and resources related to the use of machine learning for cyber security
Input/output validation framework for building reliable AI applications. Detects and mitigates risks through composable validators for PII, toxicity, prompt injection, and structured output validation. Features Guardrails Hub with 50+ pre-built validators. Apache 2.0 licensed.
NVIDIA's programmable guardrails toolkit: define input, dialog, retrieval, execution, and output rails that intercept the agent loop at five distinct layers using the Colang DSL. The execution rail layer specifically governs what tools the LLM can invoke and what their inputs/outputs may contain —…
🟢🟠— Open AI gateway with provider routing, fallback and retry controls, guardrail integrations, observability, and MCP traffic support for model and agent applications. (Portkey) — note: the gateway is general infrastructure rather than a standalone security scanner; model-provider…
Python framework for adversarial attacks, data augmentation, and model training in NLP. Augment datasets to increase model robustness and generate adversarial examples. MIT licensed.
is a Python library for secure and private Deep Learning. PySyft decouples private data from model training, using Federated Learning, Differential Privacy, and Encrypted Computation (like Multi-Party Computation (MPC) and Homomorphic Encryption (HE) within the main Deep Learning frameworks like…
A Python library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy.