Semantic Denial of Service in LLM-Controlled Robots

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases 1-5 tokens into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt...

Exploit for CVE-2025-36911

WhisperPair Exploit Toolkit CVE-2025-36911 !Python 3.8+...

CVE-2004-2451: Undefined Security Weakness

Roger Wilco 1.4.1.6 and earlier, or Roger Wilco Base Station 0.30a or earlier, allows remote attackers to send audio to arbitrary channels, aka the "Voices from the deep" bug...