#1ML-based security tools, adversarial machine learning, and AI-powered cyber defense.
Kitploit recommended
hannahxchen/llm-censorship-steeringCode for 'Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control'
mamadou-keita/deeclipImplementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"
aniketkarne/aco-prompt-shieldStop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…
jinxhy/awesome-moai-securityCurated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…
safety-research/red-teaming-auto-modeResearch code for red-teaming AI auto-mode monitors, including simulation evals, fuzzing, and monitor implementations for Claude Code and Codex…
deep-jlu/skillpoisonResearch pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…
wang-yanting/agentwatcherCausal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…
mouna23/ai-driven-mitre-attackThis repository demonstrates a machine learning pipeline for detecting MITRE ATT&CK techniques from logs and enriching the output using a local LLM.
rin449/bhpaiMulti-format malware analysis platform combining a stealth Ring-3 Windows sandbox, static PE/PDF analyzers, ransomware key recovery, and an AI…
abhinavdubey30/perturbed-embedding-vectorsCode, response logs and labels for the paper Jailbreaking Open-Weight LLMs via Random Embedding Perturbations
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…
q-rz/saffronInference scaling for LLM safety assurance
multimodal-ai-lab/tobacToken by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models (NeurIPS'26)
canonicalmg/reverse-captcha-evalEvaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…
kevinchunye/prompt_injectionBenchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…
clearlotus-git/cve-2024-37054-pocProof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…
bardlaudian/cve-2024-37054Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.
