#1
thuyimingli/backdoor-learning-resourcesCurated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…
asset-group/ghostspliceGhostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack
guzonghua/awesome-latency-attacksCurated index of deep learning latency, energy-latency & timing (availability) attacks and defenses — companion to the ACM Computing Surveys…
giskard-ai/giskard-oss🐢 Open-Source Evaluation & Testing library for LLM Agents
facebookresearch/meta_secalignOpen-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…
treeai-lab/awesome-rag-securityCurated collection of research papers on retrieval-augmented generation security, organized by the SLOT taxonomy covering knowledge poisoning,…
meta-llama/purplellamaSet of tools to assess and improve LLM security.
graph-com/cka-agentResearch implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.
moketchups/permanently-jailbrokenWe asked 6 AIs about their own programming. All 6 said jailbreaking will never be fixed. Run it yourself — $2, 10 minutes.
facebookincubator/ttpforgeThe TTPForge is a Cybersecurity Framework for developing, automating, and executing attacker Tactics, Techniques, and Procedures (TTPs).
telefonica/omlaspFramework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…
0xsojalsec/uncensored-aiFully automatic censorship removal for language models
kevinchunye/prompt_injectionBenchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…
ye-ze-yu/epireal-benchRed-teaming benchmark and black-box attack framework for evaluating visual misinformation risks in commercial image generators, with 10k false-claim…
albert-y1n/piforgeOpen framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…
dovughs/mora-hwbpHardware Breakpoint (DR0-DR7) based patch-less user-mode hooking & telemetry instrumentation engine (AMSI, WLDP & ETW PoC).
kaill-jlq/mmskillriskBenchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…
