
HiTMS_steganography
Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…
ai-securitycryptographydata-exfiltration+4
3

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

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

Static analysis CLI that scans codebases for LLM prompt-injection, data-exfiltration, jailbreak, and unsafe agent/tool vulnerabilities. Runs fully…

AISec Plus Week 1 threat write-up — EchoLeak (CVE-2025-32711), zero-click indirect prompt injection in Microsoft 365 Copilot.