Tag
Icahn School of Medicine at Mount Sinai researchers evaluate four open-weight audio-language models on verifying whether a targeted speaker (clinician or patient) was fully removed from 48 dyadic psychiatry recordings, finding that a disjunctive OR ensemble over fourteen model-view configurations achieves F1 of 0.478 driven by recall gains.
Arcjet is a runtime security platform designed to protect AI agents by detecting threats like prompt injection, authorizing tool calls, redacting sensitive data, and blocking bots and abuse in real-time.
Introduces a pure Go LLM privacy gateway that uses two-layer detection (regex and gitleaks rules) to redact PII and secrets in milliseconds without additional models/GPU, already in production.
LangChain announces that LangSmith LLM Gateway can redact sensitive data like SSNs from requests before they reach LLM providers or logs, enhancing privacy and security.