Daily, Friday 24 October 2025
Reconstructed on 19 November 2026 from archived source metadata.
From the editor
The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.
Top developments
- 1
ThreatsDay Bulletin: $176M Crypto Fine, Hacking Formula 1, Chromium Vulns, AI Hijack & More
Criminals don’t need to be clever all the time; they just follow the easiest path in: trick users, exploit stale components, or abuse trusted systems like OAuth and package registries. If your stack or habits make any of those easy, you’re already a target. This week’s…
- 2
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple strategies to circumvent their own…
- 3
BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation
The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. Though prior work has explored backdoor attacks against diffusion models for image or unconditional graph generation, those against conditional graph…
Further reading, by topic
Advisories in this window
- 7 Packagist advisories1 high · 6 moderate
- 5 Maven advisories4 moderate · 1 low
- 4 Go advisories3 high · 1 moderate
- 2 npm advisories1 high · 1 moderate
- 1 NuGet advisory1 moderate
This edition
15 developments and 19 advisories in the window. Selection and order are automatic: how stories are placed and ranked.