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 29 June 2026 · Retrospective · Covers 28 June 2026 00:00 to 29 June 2026 00:00 UTC

Read on the web

Top developments

Fuzzing Large Language Models to Elicit Hidden Behaviours

arXiv · Research · Models

An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios

arXiv · Research · AI Security, Models

Bilevel Optimization for Neural Architecture Search

arXiv · Research · Models

Trust

Agent Security Meets Regulatory Reality -- A Practitioner Systematization of Autonomous-Agent Threats and Controls in Regulated Financial Systems

arXiv · Research · AI Security, Trust

sigstore.dev and Rekor evolution

Sigstore · Analysis · Trust

Models

QuantGuard: Learnable Rounding for Repairing Quantization-Conditioned Backdoors in LLMs

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.