PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address.

Keryn Headlines

Daily, Monday 2 February 2026 · Retrospective · Covers 1 February 2026 00:00 to 2 February 2026 00:00 UTC

Read on the web

Top developments

Global AI Bias Audit for Technical Governance

arXiv · Research · Trust

Context Dependence and Reliability in Autoregressive Language Models

arXiv · Research · AI Security

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

arXiv · Research · Models

SCA

TxRay: Agentic Postmortem of Live Blockchain Attacks

arXiv · Research · SCA

SMCP: Secure Model Context Protocol

arXiv · Research · AI Security, SCA

Models

To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack

arXiv · Research · AI Security, Models

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models

arXiv · Research · Models

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents

arXiv · Research · AI Security, Models

Advisories in this window

  • 1 Go advisory · 1 high
  • 1 npm advisory · 1 moderate

All advisories

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.