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, Friday 30 May 2025 · Retrospective · Covers 29 May 2025 00:00 to 30 May 2025 00:00 UTC

Read on the web

Top developments

Cybercriminals exploit AI hype to spread ransomware, malware

BleepingComputer · Incident

LLM Agents Should Employ Security Principles

arXiv · Research · AI Security

The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets

arXiv · Research · AI Security

Trust

Resecurity Compliance Manager empowers cybersecurity leaders with AI-driven insights

Help Net Security · Analysis · Trust

Models

MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment

arXiv · Research · AI Security, Models

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

arXiv · Research · Models

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion

arXiv · Research · Models

AI Security

Securing AI Agents with Information-Flow Control

arXiv · Research · AI Security

Advisories in this window

  • 16 npm advisories · 14 critical · 2 moderate
  • 4 Go advisories · 1 critical · 2 high · 1 moderate
  • 3 PyPI advisories · 1 moderate · 2 low
  • 1 Maven advisory · 1 low
  • 1 Packagist advisory · 1 high

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.