SkillPoison
deep-jlu/skillpoisonResearch pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…
adversarial-attackai-securitymachine-learning+1
3
deep-jlu/skillpoisonResearch pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…
jisung-pacific/hdi-graphrag-attackResearch implementation of Hop-Decayed Influence (HDI) and the 3S attack framework, exposing structural auxiliary indexing vulnerabilities in…
greshake/llm-securityProof-of-concept demos and research on indirect prompt injection attacks against application-integrated LLMs, covering data exfiltration, remote…
js-lee-ai/refusal-relocatesRefusal localizes, the damage relocates, safety layers under few-sample fine-tuning
guzonghua/awesome-latency-attacksCurated index of deep learning latency, energy-latency & timing (availability) attacks and defenses — companion to the ACM Computing Surveys…
togg53192-cmd/jailbreaksCurated collection of LLM jailbreak prompts and bypass techniques, documenting adversarial inputs that circumvent AI model safety guardrails.
joshuagodwin7929/purple-team-automationAutomated adversary emulation (Caldera) against an AD lab to validate Sigma detection coverage and map results to MITRE ATT&CK.
cybershujin/prompt-injection-in-the-wildTracker of publicly reported prompt-injection techniques, broken down by delivery method, encoding, and propagation behavior, with confirmed models,…
usama1002/deleting-the-traceExperiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents
siyuanli00/intactResearch code reproducing multi-turn LLM jailbreak experiments (FITD, MRCJ, ActorAttack, X-Teaming) from the SoK intent-oriented systematization…
96kihyun/batch_jailbreakThis repository contains the official implementation of the paper "[Safety in Batches? Understanding and Mitigating Safety Failures in Batch…
chanwoochoi316/kidnapragBlack-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…
jaewonalive/camodocsResearch implementation of a poisoning attack against retrieval-augmented language models using camouflaged documents to evade filtering defenses and…
ricardojoserf/crystalpotatoCrystal port of GodPotato to abuse SeImpersonatePrivilege with indirect syscalls, dynamic API resolution and compile-time string obfuscation. Run…
bethgelab/foolboxA Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
splx-ai/agentic-radarA security scanner for your LLM agentic workflows
thuyimingli/backdoor-learning-resourcesCurated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…
robustbench/robustbenchStandardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…