bloom
safety-research/bloomAutomated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…
adversarial-attackai-securityeducation+3
1.4k
safety-research/bloomAutomated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…
canonicalmg/reverse-captcha-evalEvaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…
jd0965199-oss/ethibenchEvaluation framework for AI penetration testing agents that measures validated vulnerability discovery using LLM-based semantic matching, bipartite…
microsoft/pyritOpen-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…
gpt-laboratory/trustworthyragAn Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.
telefonica/omlaspFramework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…
erroristotle/dvdr_llmEnsemble framework for software vulnerability detection and repair using multiple large language models, with consensus analysis and evaluation tools…
vinsontang1/vultriageThe code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection
pwnhyo/t-mapTrajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…
mamadou-keita/deeclipImplementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"
phkhanhtrinh23/agasLLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…
chanwoochoi316/kidnapragBlack-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…
toxy4ny/delirium-ai-safety-benchmarkA diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…
azzzzliao/aegis-audio-defenseDefense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at…
cchio/deep-pwningMetasploit for machine learning.
albert-y1n/pismithPISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
alex66366/odpureBlack-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…