refusal-relocates
js-lee-ai/refusal-relocatesRefusal localizes, the damage relocates, safety layers under few-sample fine-tuning
adversarial-attackai-securitydefensive-tools+3
js-lee-ai/refusal-relocatesRefusal localizes, the damage relocates, safety layers under few-sample fine-tuning
facebookresearch/meta_secalignOpen-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…
atomdrift-project/scan0-day malware detection for binaries, source & scripts (that doesn't suck)
cbuijs/sdproxyDNS Proxy that is simple and fast with not so simple features. Focused on routed DNS forwarding, filtering and parental control.
norrrrrrr-lyn/wainjectbenchBenchmarking prompt injection detections for web agents.
resharma/ajarMeasuring Open Privilege in Agent Defenses
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.
openai/privacy-filterBidirectional token-classification model for PII detection and masking in text, with CLI for redaction, evaluation, and finetuning on-premises.
off-by-1-labs/flawedFix-Like Artifacts With Embedded Defects
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…
svdwi/blueboxOpen-source threat intelligence platform for malware and observable analysis. Enriches IPs, domains, URLs, and hashes with external sources, performs…
mlily2024/final-project-sql-injection-pipelineHybrid machine-learning pipelines for detecting SQL injection in web traffic, combining DistilBERT and BERT-GNN models with adversarial training and…
jianshuod/ipi-exposure-signalResearch pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…
mindcrypt/covertchannels-steganographyA list of covert channels and steganography/steganalysis resources (books, papers & tools)
cleverhans-lab/cleverhansAn adversarial example library for constructing attacks, building defenses, and benchmarking both
jaidedai/easyocrReady-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
thuyimingli/backdoor-learning-resourcesCurated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…
rob-med/awesome-ts-anomaly-detectionList of tools & datasets for anomaly detection on time-series data.