AutoRAN-public
jackpurcell/autoran-publicAutomated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…
adversarial-attackai-securityexploitation+2
11
jackpurcell/autoran-publicAutomated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…
promptfoo/promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…
meta-llama/purplellamaSet of tools to assess and improve LLM security.
togg53192-cmd/jailbreaksCurated collection of LLM jailbreak prompts and bypass techniques, documenting adversarial inputs that circumvent AI model safety guardrails.
ottosulin/awesome-ai-securityA collection of awesome resources related AI security
jiep/offensive-ai-compilationA curated list of useful resources that cover Offensive AI.
sensity-ai/dotReal-time deepfake toolkit for penetration testing of identity verification and video conferencing systems. Supports face swap, image animation, and…
trusted-ai/aif360A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in…
meridianlabs-ai/inspect_petriAn alignment auditing agent capable of quickly exploring alignment hypothesis
trusted-ai/aix360Interpretability and explainability of data and machine learning models
nextronsystems/aptsimulatorA toolset to make a system look as if it was the victim of an APT attack
owasp/aisvsThe AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…
thuyimingli/backdoor-learning-resourcesCurated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…
rosesecurity/anti-virus-evading-payloadsDuring the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…
daem0nc0re/tangledwinexecPoCs and tools for investigation of Windows process execution techniques
redteamoperations/redcloud-osRedCloudOS is a Cloud Adversary Simulation Operating System for Red Teams to assess the Cloud Security of Leading Cloud Service Providers (CSPs)
mvelazc0/purplesharpPurpleSharp is a C# adversary simulation tool that executes adversary techniques with the purpose of generating attack telemetry in monitored Windows…
vxcrypt0r/voidgateA technique that can be used to bypass AV/EDR memory scanners. This can be used to hide well-known and detected shellcodes (such as msfvenom) by…