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 6 October 2025 Retrospective Covers 5 October 2025 00:00 to 6 October 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-10-06/ TOP DEVELOPMENTS [1] MulVuln: Enhancing Pre-trained LMs with Shared and Language-Specific Knowledge for Multilingual Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2510.04397 [2] Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models arXiv · Research · https://arxiv.org/abs/2510.04347 [3] Read the Scene, Not the Script: Outcome-Aware Safety for LLMs arXiv · Research · https://arxiv.org/abs/2510.04320 SAST [4] QuiLL: An LLM-Based Vulnerability Assessment Framework for the Wild arXiv · Research · https://arxiv.org/abs/2510.04056 MODELS [5] Rounding-Guided Backdoor Injection in Deep Learning Model Quantization arXiv · Research · https://arxiv.org/abs/2510.09647 [6] COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability arXiv · Research · https://arxiv.org/abs/2510.04196 [7] From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs arXiv · Research · https://arxiv.org/abs/2510.05169 AI SECURITY [8] VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy arXiv · Research · https://arxiv.org/abs/2510.04261 [9] AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents arXiv · Research · https://arxiv.org/abs/2510.04257 ADVISORIES IN THIS WINDOW 2 PyPI advisories · 2 moderate 2 npm advisories · 1 moderate · 1 low All advisories: https://keryn.dev/headlines/advisories/ 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.