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, Tuesday 24 June 2025 · Retrospective · Covers 23 June 2025 00:00 to 24 June 2025 00:00 UTC

Read on the web

Top developments

Canadian telecom hacked by suspected China state group

Ars Technica: Security · Incident · Remediation

Echo Chamber Jailbreak Tricks LLMs Like OpenAI and Google into Generating Harmful Content

The Hacker News · Research · Models

Malware on Google Play, Apple App Store stole your photos—and crypto

BleepingComputer · Incident

Remediation

Design high-confidence computers using trusted instructional set architecture and emulators

arXiv · Research · Remediation

Trust

Trusting AI Models in Kubernetes: Introducing the Sigstore Model Validation Operator

Sigstore · Announcement · Trust

Models

Command-V: Pasting LLM Behaviors via Activation Profiles

arXiv · Research · Models

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models

arXiv · Research · Models

AI Security

Enhancing Security in LLM Applications: A Performance Evaluation of Early Detection Systems

arXiv · Research · AI Security

Google Adds Multi-Layered Defenses to Secure GenAI from Prompt Injection Attacks

The Hacker News · Analysis · AI Security

Advisories in this window

  • 32 npm advisories · 31 critical · 1 high
  • 4 PyPI advisories · 2 high · 1 moderate · 1 low
  • 2 crates.io advisories · 1 moderate · 1 low
  • 1 Maven advisory · 1 moderate
  • 1 Go advisory · 1 low

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.