Saturday, 12 October 2024

Keryn Headlines

Daily Retrospective

Covers 11 October 2024 00:00 to 12 October 2024 00:00 UTC

Daily, Saturday 12 October 2024

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 AgentHarm: A Benchmark for Measuring Harmfulness of LLM AgentsarXiv

Top developments

  1. 1

    AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

    The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external tools and can execute multi-stage…

    arXiv · Research · 11 October 2024 · Models

  2. 2

    Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks

    As machine learning models become increasingly complex, concerns about their robustness and trustworthiness have become more pressing. A critical vulnerability of these models is data poisoning attacks, where adversaries deliberately alter training data to degrade model…

    arXiv · Research · 11 October 2024 · Models

  3. 3

    PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning

    Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models' susceptibility to data poisoning during…

    arXiv · Research · 11 October 2024 · Models

Further reading, by topic

SCA

  1. 4

Models

  1. 5
  2. 6

AI Security

  1. 7

Advisories in this window

  • 18 npm advisories17 critical · 1 high
  • 2 PyPI advisories1 moderate · 1 low
  • 2 Go advisories1 critical · 1 moderate
  • 1 Maven advisory1 critical
  • 1 Multi-ecosystem advisory1 critical
  • 1 Packagist advisory1 high

All advisories

This edition

9 developments and 25 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.