Daily, Monday 22 June 2026
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
VeriPort: Automated and Verified Patch Backporting at Scale
One of the key challenges for securing the software supply chain is addressing known vulnerabilities in third-party open-source dependencies. Security patches are frequently only available for the latest version of a dependency, leaving developers with the choice of either…
- 2
SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors
Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising paradigm for privacy-sensitive applications. However, its decentralized nature makes it inherently vulnerable to backdoor attacks, where malicious clients embed hidden…
- 3
The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque. In this work, we investigate whether safety compliance is a deep semantic decision or a manipulable linear feature. We introduce Contrastive Logit…
Further reading, by topic
Advisories in this window
- 10 PyPI advisories1 critical · 2 moderate · 7 low
This edition
7 developments and 10 advisories in the window. Selection and order are automatic: how stories are placed and ranked.