PyRIT
microsoft/pyritOpen-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…
adversarial-attackai-securitymachine-learning+2
4.7k
microsoft/pyritOpen-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…
jaidedai/easyocrReady-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
usama1002/deleting-the-traceExperiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents
google/magikaFast and accurate AI powered file content types detection
lucamassarelli/yarasafeSAFE embeddings to match functions in yara
toxy4ny/redteam-ai-benchmarkRed Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks. Red Team AI Benchmark is a CLI model-evaluation benchmark. It…
spamscanner/spamscannerSpam Scanner is a Node.js anti-spam, email filtering, and phishing prevention tool and service. Built for @ladjs, @forwardemail, @cabinjs, @breejs,…
cyberforce/pesidiousMalware Mutation Using Reinforcement Learning and Generative Adversarial Networks
ait-aecid/logdata-anomaly-minerThis tool parses log data and allows to define analysis pipelines for anomaly detection. It was designed to run the analysis with limited resources…
stratosphereips/manatiA web-based tool to assist the work of the intuitive threat analysts.
benjeems/packetstriderA network packet forensics tool for SSH
visma-prodsec/columboML-assisted forensic analysis tool that automates memory, disk, and live system triage on Windows using Volatility 3, autorunsc, and sigcheck to…
trustedsec/ts_llmlibPython library for local LLM-powered security analysis with Ghidra binary analysis, C/C++ vulnerability scanning, and MCP tool integration for…
bishopfox/brokenhillA productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)
wsu-cyber-security-lab-ai/clipguardAdversarial image perturbation tool that uses SAM segmentation and CLIP models to evade AI-based scam image classifiers for security research.
trailofbits/anamorpherimage scaling attacks for multi-modal prompt injection
toxy4ny/delirium-ai-safety-benchmarkA diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…
rushter/hexoraStatic analysis of malicious Python code