Artificial Intelligence & Ethics

Global: New Learnable Framework Detects Unseen Jailbreak Attacks on Vision-Language ModelsResearchers have introduced a novel detection system called Learning to Detect (LoD) in a recent arXiv preprint, aiming to identify…

Global: Study Finds Simple Prefix Fine‑Tuning Can Undermine LLM Safety Refusals Researchers have identified a previously unexplored vulnerability in the safety alignment of large language models (LLMs), according to a…

Global: Study Assesses Amazon’s Frontier Model Safety Framework on Nova 2.0 LiteResearchers including Satyapriya Krishna, Matteo Memelli, and colleagues published a detailed assessment of Amazon’s Frontier Model Safety Framework (FMSF)…

Global: EM-MIA Enhances Membership Inference Attacks on Language Models Without Labeled Non-Members Researchers have introduced EM-MIA, an expectation‑maximization based membership inference approach that operates without the need for labeled non‑member…

Global: Detection of Prompt Injection Attacks in LLM-Integrated ApplicationsA team of researchers announced a novel detection technique, PIShield, aimed at identifying prompt injection attacks that compromise large language model (LLM)…

Global: Researchers Reveal New Gradient Inversion Attack Targeting Adapter-Based Federated LLMsA team of machine‑learning researchers announced in January 2026 that they have developed a novel gradient inversion technique capable of…

Global: New Framework Aims to Streamline Evaluation and Training of Healthcare Language ModelsOn Jan. 26, 2026, researchers Zhichao Yang, Sepehr Janghorani, Dongxu Zhang, Jun Han, Qian Qian, Andrew Ressler II,…

Global: Prefill Prompting Enhances Zero-Shot Detection of AI-Generated Images Researchers from the University of Arizona and collaborators have introduced a prompting technique that improves the ability of vision‑language models (VLMs)…

Global: Distributed Graph-Attention Framework Advances Multi-Agent Reinforcement LearningA team of researchers announced a novel distributed multi-agent reinforcement learning (MARL) framework that eliminates the need for centralized critics and global state…

Global: Study Proposes Verification-First AI to Preserve Integrity of Peer ReviewA paper submitted on Jan. 23, 2026, by Lei You, Lele Cao, and Iryna Gurevych argues that AI‑assisted peer review should prioritize verification…