
awesome-ai-security
A collection of awesome resources related AI security

A collection of awesome resources related AI security

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

Fully automatic censorship removal for language models

A curated collection of resources for learning and researching LLM prompt injection attacks, defenses, and security.

An alignment auditing agent capable of quickly exploring alignment hypothesis

CVE-2026-20685 - Draft or TODO

Production AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities.…

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

reverse engineering Gemini's SynthID detection

Fully automatic censorship removal for language models

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

A list of useful Powershell scripts with 100% AV bypass (At the time of publication).

Adversary simulation and Red teaming platform with AI

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

Automated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…