T-MAP
pwnhyo/t-mapTrajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…
adversarial-attackai-securitymachine-learning+3
18
pwnhyo/t-mapTrajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…
qkrrkd90-source/weavemarkReference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…
cucu220123/safety-awarenessResearch code for extracting and training safety-awareness directions in multimodal LLMs to improve refusal behavior while limiting benign-task drift.
shuangliangx/learning-to-detectDetects unknown jailbreak attacks in large vision-language models using hidden state analysis and autoencoders, with training and evaluation…
binzhwang/tnc-defenseResearch code for detecting and detoxifying backdoors in text-to-image diffusion models, with pipelines for Stable Diffusion v1.4, v1.5, XL, and 3…
tracebyte8/systraceLinux system-call monitor using ptrace to trace file, process, network, and memory activity, with namespace isolation and machine learning…
mindcrypt/covertchannels-steganographyA list of covert channels and steganography/steganalysis resources (books, papers & tools)
trusted-ai/adversarial-robustness-toolboxPython library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…
cleverhans-lab/cleverhansAn adversarial example library for constructing attacks, building defenses, and benchmarking both
bethgelab/foolboxA Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
jaidedai/easyocrReady-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
jiep/offensive-ai-compilationA curated list of useful resources that cover Offensive AI.
microsoft/pyritOpen-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…
microsoft/responsible-ai-toolboxInteractive dashboards and libraries for responsible AI model debugging, covering error analysis, fairness, interpretability, counterfactuals, causal…
nvidia-nemo/guardrailsProgrammable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…
trusted-ai/aif360A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in…
hydradragonantivirus/hydradragonav-mobileAndroid Antivirus which doesn't require root, adb, ca install and cloud with many features and ways to detect more zero-day malware
yingtaoren/d-scanAnalyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.