Daily, Monday 16 June 2025
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
An Introduction to Google’s Approach to AI Agent Security
Here's another new paper on AI agent security: An Introduction to Google’s Approach to AI Agent Security , by Santiago Díaz, Christoph Kern, and Kara Olive. (I wrote about a different recent paper, Design Patterns for Securing LLM Agents against Prompt Injections just a few…
- 2
Jailbreak Transferability Emerges from Shared Representations
Jailbreak transferability is the surprising phenomenon when an adversarial attack compromising one model also elicits harmful responses from other models. Despite widespread demonstrations, there is little consensus on why transfer is possible: is it a quirk of safety training,…
- 3
Universal Jailbreak Suffixes Are Strong Attention Hijackers
We study suffix-based jailbreaks$\unicode{x2013}$a powerful family of attacks against large language models (LLMs) that optimize adversarial suffixes to circumvent safety alignment. Focusing on the widely used foundational GCG attack, we observe that suffixes vary in efficacy:…
Further reading, by topic
Models
- 4
- 5
- 6
This edition
8 developments and 0 advisories in the window. Selection and order are automatic: how stories are placed and ranked.