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

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

Runtime governance for AI agents. Allow, warn, or block every model and tool call before it commits. Hash-chained audit for every decision.…

Fingerprint OpenAI-compatible LLMs from tokenizer and behavior signals.

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

Browser extension that detects PII and sensitive data in AI chats, masks it with placeholders before sending, and restores originals in replies—all…

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

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo:…

AI powered security analysis extension for Mobile Security Framework MobSF

CAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…

Bypass restricted and censored content on AI chat prompts 😈