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
4.4k
microsoft/pyritOpen-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…
toxy4ny/delirium-ai-safety-benchmarkA diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…
bishopfox/brokenhillA productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)
cyberforce/pesidiousMalware Mutation Using Reinforcement Learning and Generative Adversarial Networks
canonicalmg/reverse-captcha-evalEvaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…
safety-research/bloomAutomated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…
c3rb3ru5d3d53c/binlexA Binary Genetic Traits Lexer Framework
telefonica/omlaspFramework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…
pwnhyo/t-mapTrajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…
trailofbits/anamorpherimage scaling attacks for multi-modal prompt injection
chanwoochoi316/kidnapragBlack-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…
sbamit/exponentiated-gradient-descent-llm-attackA novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.
paul12345-cyber/multimodal-web-attack-datasetThis repository hosts a multimodal web attack dataset (MWAD) to advance AI-driven threat detection research.
xueboqiu/prohunterGraph-based threat detection system using inexact graph vector matching to compare threat graphs with CTI-derived attack query graphs for automated…
davidc1212/crawRobust audio watermarking framework embedding binary messages into magnitude spectrograms, with differentiable attack simulation, Q-Former pooling,…
protectai/rebuffMulti-layered prompt injection detector for AI applications using heuristics, LLM-based analysis, vectorDB attack signatures, and canary token leak…
skac44/cve-2024-38063Simulates CVE-2024-38063 TCP/IP remote code execution attack, captures network traffic with TShark, and trains a machine learning model to detect…
blevene/standalone_tdoExtracts structured Cyber Threat Intelligence (CTI) from PDF, DOCX, and TXT documents using LLMs. Generates MITRE ATT&CK attack flows, detection…