heretic
p-e-w/hereticTraining-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
adversarial-attackai-securityeducation+3
p-e-w/hereticTraining-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
nvidia/garakModular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…
promptfoo/promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…
nousresearch/hermes-agentThe agent that grows with you
huhusmang/awesome-llms-for-vulnerability-detectionThe community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers…
francescopace/espectreESPectre - Motion detection system based on Wi-Fi spectre analysis (CSI), with Home Assistant integration.
sparkyniner/netryx-astra-v2-geolocation-toolThe world's most sophisticated street level image geolocation software
zju-llm-safety/darwinEvolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…
0xsojalsec/uncensored-aiFully automatic censorship removal for language models
thuyimingli/backdoor-learning-resourcesCurated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…
facebookresearch/meta_secalignOpen-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…
guzonghua/awesome-latency-attacksCurated index of deep learning latency, energy-latency & timing (availability) attacks and defenses — companion to the ACM Computing Surveys…
graph-com/cka-agentResearch implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.
telefonica/omlaspFramework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…
openclaw/openclawThe AI that really does things. Any OS. Any Platform. The lobster way. 🦞
kevinchunye/prompt_injectionBenchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…
screenpipe/screenpipeYC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power…