Ai Safety

GarakPython

A command-line tool for red-teaming and vulnerability scanning of large language models (LLMs).

Awesome Machine Learning Interpretability

A curated list of practical resources for responsible machine learning, covering interpretability, governance, safety, and ethics.

ImitationPython

Clean PyTorch implementations of imitation and reward learning algorithms for reinforcement learning.

prompt-injection-defenses

A centralized repository summarizing practical and proposed defenses against prompt injection attacks on large language models.

Prompt Injection

A curated list of resources for understanding, detecting, and mitigating prompt injection attacks against machine learning models.

Awesome Adversarial Deep Learning

A curated collection of resources on adversarial examples in deep learning, covering attacks, defenses, and applications.

Safety in Embodied AI: Risks, Attacks, and DefensesShell

A comprehensive survey and unified safety framework for embodied AI, covering 400+ papers on risks, attacks, and defenses across perception, cognition, planning, interaction, and agentic systems.

InjecGuardPython

An open-source prompt guard model that detects prompt injection attacks while mitigating over-defense against benign inputs.