
reverse-SynthID-text
reverse engineering SynthID for text

reverse engineering SynthID for text

DNS Proxy that is simple and fast with not so simple features. Focused on routed DNS forwarding, filtering and parental control.

DGA Domain Detection using Bigram Frequency Analysis

Diagnostic LLM safety benchmark with 3,489 bilingual prompts, an 84-label taxonomy, and prompt-level rubric judging for explainable, fine-grained…


Cyber Threat Defense World Modeling

finance domain specific red-teaming benchmark evaluation rubric

Reference implementation of privacy-preserving face recognition using replicated secret sharing in MP-SPDZ, with quantized GhostFaceNet inference,…

Hide valuable information where it's least expected

Public version of the Entropica repo

Black-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…

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

Customer Assurance Operating System. Answer the security questionnaires your customers send you, once.

Multi-layered prompt injection detector for AI applications using heuristics, LLM-based analysis, vectorDB attack signatures, and canary token leak…

Bidirectional token-classification model for PII detection and masking in text, with CLI for redaction, evaluation, and finetuning on-premises.

AI-powered threat intelligence platform for automated CVE/ransomware monitoring, domain surveillance, data leak detection, and incident response with…

reverse of openai privacy filter. same 1.5b model, returns pii as structured spans instead of masking

Automating Host Exploitation with AI