
HiTMS_steganography
Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Hunting for passwords with deep learning


A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)


A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.


Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

QuantumLock is an open-source, quantum-resistant Bitcoin protocol designed to protect digital assets from future quantum computing threats. Featuring…


Security Scanner for Agent Skills


The repository that contains the algorithms for generating domain names, dictionaries of malicious domain names. Developed to research the…


Reverse of OpenAI Privacy Filter: same 1.5B model, returns PII as structured spans instead of masking.

Asymmetric defense against adversarial AI agents. VeilGate evaluates each incoming request, redirects suspected agents into a per-IP-consistent…

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