Monday, 2 February 2026

Keryn Headlines

Daily Retrospective

Covers 1 February 2026 00:00 to 2 February 2026 00:00 UTC

Daily, Monday 2 February 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.

1 Global AI Bias Audit for Technical GovernancearXiv

Top developments

  1. 1

    Global AI Bias Audit for Technical Governance

    This paper presents the outputs of the exploratory phase of a global audit of Large Language Models (LLMs) project. In this exploratory phase, I used the Global AI Dataset (GAID) Project as a framework to stress-test the Llama-3 8B model and evaluate geographic and…

    arXiv · Research · 1 February 2026 · Trust

  2. 2

    Context Dependence and Reliability in Autoregressive Language Models

    Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which context elements actually influence the…

    arXiv · Research · 1 February 2026 · AI Security

  3. 3

    Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

    Diffusion language models (DLMs) have recently emerged as a competitive alternative to autoregressive (AR) models, offering parallel decoding, competitive generation quality, and initial evidence of improved jailbreak robustness. Despite this progress, the role of sampling…

    arXiv · Research · 1 February 2026 · Models

Further reading, by topic

SCA

  1. 4

    TxRay: Agentic Postmortem of Live Blockchain Attacks

    arXiv · Research · 1 February 2026

  2. 5

    SMCP: Secure Model Context Protocol

    arXiv · Research · 1 February 2026

Models

  1. 6
  2. 7
  3. 8

Advisories in this window

  • 1 Go advisory1 high
  • 1 npm advisory1 moderate

All advisories

This edition

8 developments and 2 advisories in the window. Selection and order are automatic: how stories are placed and ranked.

Follow Keryn Headlines

Security news for teams building with AI. Choose an edition:

  • Daily: Every morning, 06:00 UTC. A short operational briefing: the few developments that matter, who is affected and what to watch. RSS feed
  • Weekly: Tuesdays, about 07:00 US Eastern. The week in order of importance. An editor’s essay accompanies the edition when it passes editorial checks. RSS feed
  • Monthly: The first Tuesday of the month, about 07:00 US Eastern. The month in review. A long read accompanies the edition when it passes editorial checks. RSS feed

Email is not open yet

Use RSS now: it works in any feed reader and needs no sign-up. Add the feed for the edition you want.

Daily feedWeekly feedMonthly feed All editions

When email opens, this box will let you choose editions and confirm by email. Nothing is collected before then.