PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address.

Keryn Headlines

Daily, Sunday 15 June 2025 · Retrospective · Covers 14 June 2025 00:00 to 15 June 2025 00:00 UTC

Read on the web

Top developments

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models

arXiv · Research · Models

When Forgetting Triggers Backdoors: A Clean Unlearning Attack

arXiv · Research · Models

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

arXiv · Research · Models

SCA

Information-theoretic Estimation of the Risk of Privacy Leaks

arXiv · Research · SCA

Trust

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models

arXiv · Research · Models, Trust

Models

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning

arXiv · Research · Models

Exploring the Secondary Risks of Large Language Models

arXiv · Research · Models

QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety

arXiv · Research · Models

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.