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 28 June 2026 · Retrospective · Covers 27 June 2026 00:00 to 28 June 2026 00:00 UTC

Read on the web

Top developments

A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization

arXiv · Research · Models

Symbolon: Symbolic Execution by Learning Code Transformation

arXiv · Research · SAST

From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

arXiv · Research · AI Security

SCA

Understanding Binary Code Similarity for Real-World Vulnerability Detection: A Large-Scale Empirical Study

arXiv · Research · SCA

Agentic SDLC

Clean GitHub repo tricks AI coding agents into running malware

BleepingComputer · Analysis · Agentic SDLC, AI Security

Trust

Cybersecurity is the True Frontier for Generative AI Success or Failure

arXiv · Research · Trust

Models

FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks

arXiv · Research · Models

AI Security

An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis

arXiv · Research · AI Security

Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare

arXiv · Research · AI Security

Advisories in this window

  • 3 npm advisories · 3 high

All advisories

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.