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, Monday 17 November 2025 · Retrospective · Covers 16 November 2025 00:00 to 17 November 2025 00:00 UTC

Read on the web

Top developments

LLM Reinforcement in Context

arXiv · Research · Models

On Robustness of Linear Classifiers to Targeted Data Poisoning

arXiv · Research · Models

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

arXiv · Research · Models

SCA

AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework

arXiv · Research · AI-BOM, SCA

Models

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks

arXiv · Research · Models

Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments

arXiv · Research · AI Security, Models

GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

arXiv · Research · AI Security, 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.