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 24 October 2025 · Retrospective · Covers 23 October 2025 00:00 to 24 October 2025 00:00 UTC

Read on the web

Top developments

ThreatsDay Bulletin: $176M Crypto Fine, Hacking Formula 1, Chromium Vulns, AI Hijack & More

The Hacker News · Incident · SCA

Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training

arXiv · Research · Models

BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation

arXiv · Research · Models

SAST

Learning to Triage Vulnerability Reports from Program Analysis: An Empirical Study in Node.js

arXiv · Research · Remediation, SAST

SCA

NeuPerm: Disrupting Malware Hidden in Neural Network Parameters by Leveraging Permutation Symmetry

arXiv · Research · SCA

Classport: Designing Runtime Dependency Introspection for Java

arXiv · Research · SCA

Trust

Get up to Speed on FedRAMP 20x

Chainguard · Analysis · Trust

Models

Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations

arXiv · Research · Models

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models

arXiv · Research · Models

AI Security

GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?

arXiv · Research · AI Security

Advisories in this window

  • 7 Packagist advisories · 1 high · 6 moderate
  • 5 Maven advisories · 4 moderate · 1 low
  • 4 Go advisories · 3 high · 1 moderate
  • 2 npm advisories · 1 high · 1 moderate
  • 1 NuGet 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.