
robin
AI-powered dark web OSINT tool that uses LLMs to refine queries, filter search results, and generate investigation summaries with a web UI and Docker…

AI-powered dark web OSINT tool that uses LLMs to refine queries, filter search results, and generate investigation summaries with a web UI and Docker…

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

Open-source interactive security awareness training library with 130+ SCORM exercises covering phishing, vishing, BEC, MFA fatigue, and OWASP AI/LLM…

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

Research-only AI watermark robustness toolkit: local reverse proxy strips C2PA/EXIF/XMP, Unicode, image/audio stego, OOXML/PDF metadata, and scans…

A privacy-first app that strips AI watermarks from content you own.

cMCP: Confidential MCP Gateway. Hardware-attested policy enforcement for MCP tool calls.

PISIGuard runs entirely in your browser. It spots names, email addresses, phone numbers, credit card numbers, passwords, API keys, and more, replaces…

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

Code for the paper Certified Unlearning for Neural Networks, ICML 2025

The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)

A small Rust CLI that strips secrets from your clipboard on demand.

EmailXpose is an open source AI-powered email security system that detects phishing, spam, scams, malware, and social engineering attacks. It goes…

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins…