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 17 February 2025 · Retrospective · Covers 16 February 2025 00:00 to 17 February 2025 00:00 UTC

Read on the web

Top developments

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs

arXiv · Research · Models

VulRG: Multi-Level Explainable Vulnerability Patch Ranking for Complex Systems Using Graphs

arXiv · Research · Remediation

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems

arXiv · Research · AI Security, Models

Models

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

arXiv · Research · Models

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models

arXiv · Research · Models

Prompt Inject Detection with Generative Explanation as an Investigative Tool

arXiv · Research · Models

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.