HDI-GraphRAG-Attack
jisung-pacific/hdi-graphrag-attackResearch implementation of Hop-Decayed Influence (HDI) and the 3S attack framework, exposing structural auxiliary indexing vulnerabilities in…
adversarial-attackai-securitydata-exfiltration+3
5
jisung-pacific/hdi-graphrag-attackResearch implementation of Hop-Decayed Influence (HDI) and the 3S attack framework, exposing structural auxiliary indexing vulnerabilities in…
uiuc-kang-lab/persistbdResearch code for training adapters that make LLM agent backdoors survive benign fine-tuning, with trigger-rate scoring, SWE-bench evaluation, and…
josh-blythe/bordair-detectorTwo-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…
mthamil107/db_audit_researchSelf-Defeating Audits: reproducible lab showing a low-privilege PostgreSQL role reversibly blinding a trigger-based auditor + poisoning attribution…
pedrobarcha/memory-injectionResearch on persistent prompt injections via memory features in Claude, Gemini, and ChatGPT, with reproduction steps, datasets, and proofs for…
euph00/zoneclaw-codeBenchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…
xiaoyan-lisa/defenses-for-tool-integrated-llmResearch code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…
suels-group/beyond_asrResearch code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…
thuname/tedResearch artifact from USENIX Security 2026 demonstrating DDoS attacks by abusing tunnel nodes and IPv6 extension headers, with accompanying analysis…
pixee/compaction-launderingSecurity research on context compaction in coding agents: shows how forged role labels in untrusted content survive summarization and get executed,…
trusted-ai/aix360Interpretability and explainability of data and machine learning models
helviojunior/hookchainHookChain: A new perspective for Bypassing EDR Solutions
0xsojalsec/uncensored-aiFully automatic censorship removal for language models
gmh5225/awesome-ai-securityA curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.
zju-llm-safety/darwinEvolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…
zju-llm-safety/ascentFine-tuning framework that applies first-order optimal safety calibration and periodic recalibration to LLMs, preserving safety-compatible updates…
lsudoko/antibodyGitLab Duo DevSecOps loop where a second AI re-attacks every AI-written fix, saving each successful bypass as a permanent antibody replayed in CI and…
jiep/offensive-ai-compilationA curated list of useful resources that cover Offensive AI.