#1Adversarial ML attack frameworks, evasion techniques, and model robustness evaluation tools.
Kitploit recommended
pppyb/secopdResearch implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…
pwnhyo/t-mapTrajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…
d0rb/eclipse-chatgpt-4o-jailbreakMeet Eclipse the only jailbreak that moonwalks around ChatGPT 4o.
moketchups/permanently-jailbrokenWe asked 6 AIs about their own programming. All 6 said jailbreaking will never be fixed. Run it yourself — $2, 10 minutes.
treeai-lab/awesome-rag-securityCurated collection of research papers on retrieval-augmented generation security, organized by the SLOT taxonomy covering knowledge poisoning,…
jackpurcell/autoran-publicAutomated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…
abhinavdubey30/perturbed-embedding-vectorsCode, response logs and labels for the paper Jailbreaking Open-Weight LLMs via Random Embedding Perturbations
andyshaw01/poisoncraftThis repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.
cybershujin/prompt-injection-in-the-wildTracker of publicly reported prompt-injection techniques, broken down by delivery method, encoding, and propagation behavior, with confirmed models,…
zjuicsr/deeptrapSecurity benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…
dtrizna/quasarnixReverse Shell Detection with Machine Learning
asset-group/ghostspliceGhostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack
deep-jlu/skillpoisonResearch pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…
xuyw-seu/packetpatchPractical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.
jpoindexter/interrogation-gameVoice-based detective interrogation game. Mistral Large 3 + Voxtral STT + ElevenLabs TTS. Built for the Mistral Worldwide Hackathon 2026.
ml-security-research-lab/cachetrapResearch code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.
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"
