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 8 December 2025 Retrospective Covers 7 December 2025 00:00 to 8 December 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-12-08/ TOP DEVELOPMENTS [1] A Technical Policy Blueprint for Trustworthy Decentralized AI arXiv · Research · https://arxiv.org/abs/2512.11878 [2] SoK: Trust-Authorization Mismatch in LLM Agent Interactions arXiv · Research · https://arxiv.org/abs/2512.06914 [3] Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models arXiv · Research · https://arxiv.org/abs/2512.06899 MODELS [4] Graph-Regularized Sparse Autoencoders for LLM Safety Steering arXiv · Research · https://arxiv.org/abs/2512.06655 AI SECURITY [5] SIEVE: Selective Integrity Verification and Escalation for Defending LLM Agents against Indirect Prompt Injection arXiv · Research · https://arxiv.org/abs/2512.06716 Titles, links and short excerpts only; every item links to its source. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.