bloom
safety-research/bloomAutomated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…
adversarial-attackai-securityeducation+3
1.4k
safety-research/bloomAutomated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…
thunlp/openattackAn Open-Source Package for Textual Adversarial Attack.
marcnewlin/hi_my_name_is_keyboardBluetooth keystroke injection exploit PoCs for CVE-2023-45866, CVE-2024-21306, and CVE-2024-0230 targeting Android, Linux, macOS, and iOS via…
0xsojalsec/uncensored-aiFully automatic censorship removal for language models
robustbench/robustbenchStandardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…
arosenmund/defcon33_silence_kill_edrHands-on DEFCON workshop materials for killing and silencing EDR agents: lab setup, BYOVD, custom C/C++ evasion tooling, and reverse engineering.
nmantani/archiver-motw-support-comparisonCompares Windows archiver support for Mark of the Web propagation, helping teams assess which tools preserve MOTW and mitigate macro-based malware…
doctoreww/evilfonttoolA font-based deception tool for red teaming, security research, and whatever else.
praetorian-inc/augustusLLM security testing framework for detecting prompt injection, jailbreaks, and adversarial attacks — 190+ probes, 28 providers, single Go binary
daem0nc0re/atomicsyscallTools and PoCs for Windows syscall investigation.
binderlabs/dircreate2systemWeaponizing to get NT SYSTEM for Privileged Directory Creation Bugs with Windows Error Reporting
santanderai/autoguardrailsAlignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
gmh5225/awesome-ai-securityA curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.
darkcodersc/sharpftpc2A Streamlined FTP-Driven Command and Control Conduit for Interconnecting Remote Systems.
knoveleng/redeval[ICLR 2026] - Official repo for the paper: "RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models"
secml/secmlA Python library for Secure and Explainable Machine Learning Documentation available @ https://secml.gitlab.io Follow us on Twitter @…
suraj-ranganath/stealthrlStealthRL: RL framework for adversarially paraphrasing AI text to stress-test detector robustness.
telefonica/omlaspFramework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…