Research & Innovation

Global: Evaluation of Implicit Regulatory Compliance in LLM Tool InvocationResearchers from several universities and industry labs submitted a paper to arXiv on Jan 13 2026 describing a new framework, LogiSafetyGen, that translates…

Global: New Attack Compromises Fairness in Federated Learning ModelsA novel attack vector targeting fairness in federated learning models has been detailed in a recent preprint. The study, posted on arXiv,…

Global: Survey Analyzes Advances and Trade‑offs in Speedy Secure Finality for EthereumTwo computer scientists, Yash Saraswat and Abhimanyu Nag, released a state‑of‑the‑art survey on Speedy Secure Finality (SSF) in a…

Global: Reproducibility Study Confirms Effectiveness of API Call Frequency Malware DetectionResearchers led by Juhani Merilehto submitted a preprint on January 13, 2026 that independently reproduces a previously published malware detection…

Global: Researchers Examine Trustless Bribery Contracts Targeting Ethereum ValidatorsOn January 13, 2026, a team of six scholars from multiple institutions released a revised version of their study on Ethereum consensus…

Global: Estimating the True Distribution of Data Collected with Randomized ResponseResearchers from multiple institutions have introduced a simple closed‑form solution for the maximum‑likelihood estimate (MLE) of data gathered through randomized…

Global: Study Reveals Control-Flow Flaw Weakens MACPRUNING Defense for DNN Side-Channel ProtectionA research team led by Ding and colleagues presented findings that a previously unexamined control‑flow dependency can substantially compromise…

Global: SafeRedir Framework Enables Inference‑Time Unlearning for Image Generation ModelsBackground and MotivationResearchers have introduced SafeRedir, an inference‑time framework designed to remove unsafe concepts from image generation models without altering the…

Global: Automated Platform Evaluates Security of Web AgentsResearchers led by Xinyi Wu and five co‑authors introduced an automated platform named WebTrap Park that systematically assesses the security of web agents by…

Global: Baiting AI: Deceptive Adversary Against AI-Protected Industrial InfrastructuresA team of researchers led by Aryan Pasikhani, Prosanta Gope, Yang Yang, Shagufta Mehnaz, and Biplab Sikdar submitted a paper on 13…