Daily, Sunday 12 April 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
Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
Large language models remain vulnerable to jailbreak attacks -- inputs designed to bypass safety mechanisms and elicit harmful responses -- despite advances in alignment and instruction tuning. We propose Head-Masked Nullspace Steering (HMNS), a circuit-level intervention that…
- 2
STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems
Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability surface before deployment, but it cannot determine whether a particular invocation is unsafe under the current user request and…
- 3
Organizational Security Resource Estimation via Vulnerability Queueing
We provide an approach that closely estimates an organization's cyber resources directly from vulnerability timestamps, using a non-stationary queueing framework. Traditional attack-surface metrics operate on static snapshots, ignoring the core attack-defense dynamics within…
Further reading, by topic
Advisories in this window
- 1 PyPI advisory1 critical
This edition
4 developments and 1 advisories in the window. Selection and order are automatic: how stories are placed and ranked.