Saturday, 31 January 2026

Keryn Headlines

Daily Retrospective

Covers 30 January 2026 00:00 to 31 January 2026 00:00 UTC

Daily, Saturday 31 January 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 Case study: Securing AI application supply chainsMicrosoft

Top developments

  1. 1

    Case study: Securing AI application supply chains

    Securing AI-powered applications requires more than just safeguarding prompts. Organizations must adopt a holistic approach that includes monitoring the AI supply chain, assessing frameworks, SDKs, and orchestration layers for vulnerabilities, and enforcing strong runtime…

    Microsoft · Research · 30 January 2026 · AI-BOM

  2. 2

    Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode

    Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation efficiency. Beyond the utility benefits, we argue that D-LLMs exhibit a previously underexplored safety blessing: their diffusion-style…

    arXiv · Research · 30 January 2026 · Models

  3. 3

    "Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval

    Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated that such LLM-based Retrieval (LLMR) is…

    arXiv · Research · 30 January 2026 · Models

Further reading, by topic

SAST

  1. 4
  2. 5
  3. 6

SCA

  1. 7

    MITRE ATLAS (releases) v5.3.0

    MITRE · Release · 30 January 2026

  2. 8
  3. 9

    Protect your AI workloads from supply chain attacks

    Chainguard · Analysis · 30 January 2026

DAST

  1. 10

    Rust and Go directed fuzzing with LibAFL-DiFuzz

    arXiv · Research · 30 January 2026

Agentic SDLC

  1. 11

Remediation

  1. 12
  2. 13
  3. 14

Trust

  1. 15

Models

  1. 16

    MITRE ATLAS (releases) v5.2.0

    MITRE · Release · 30 January 2026

  2. 17
  3. 18

AI Security

  1. 19
  2. 20

Advisories in this window

  • 5 PyPI advisories1 critical · 3 high · 1 low
  • 3 npm advisories1 critical · 1 high · 1 low
  • 1 Packagist advisory1 moderate
  • 1 Maven advisory1 high
  • 1 NuGet advisory1 moderate

All advisories

This edition

39 developments and 11 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.