Cybersecurity & Exploits

Global: Personalized Phishing Detection Leveraging LLMs and Retrieval-Augmented Generation Shows High AccuracyA new study released on arXiv outlines a personalized email security framework that combines large language models (LLMs) with…

Global: Study Examines Virtualization-Based Attacks on Asian Banking AppsA research paper submitted on 29 January 2026 by Wei Minn and eight co‑authors investigates how a virtualization‑based malware, named FjordPhantom, exploits…

Global: Study Finds Major Gaps in Brand Smishing GuidanceResearchers analyzed the public-facing smishing education materials of 149 well‑known brands spanning 25 industry categories to assess how these companies inform customers…

Global: Study Unveils Penalty-Based Backdoor Framework Targeting Object Detection ModelsA research team led by Kealan Dunnett and colleagues released a paper on 28 Jan 2026 describing BadDet+, a penalty‑based framework…

Global: LLM-Based Detection of Cyberattacks on Transformer RelaysA new study demonstrates that compact large language models can be adapted to identify cyberattacks targeting transformer current differential relays (TCDRs), which are…

Global: What is the AGI in Offensive Security?A paper submitted on 27 January 2026 by Youngwoong Cho proposes a formal framework that treats offensive security activities as instances of symbolic…

Global: Security Benchmark of Llama Models Reveals Smaller Guard Variants Outperform Larger Base ModelsIn January 2026, a team of researchers published a benchmark study evaluating the security performance of various…

Global: Survey Highlights Emerging Security Risks for AI Agents in Cyber‑Physical SystemsA new arXiv preprint (arXiv:2601.20184) provides a comprehensive review of security threats targeting artificial‑intelligence agents embedded in cyber‑physical systems…

Global: Researchers Propose UnlearnShield to Counter Unlearning Inversion AttacksOn January 28, 2026, a group of nine researchers—including Lulu Xue, Shengshan Hu, Wei Lu, Ziqi Zhou, Yufei Song, Jianhong Cheng, Minghui…

Global: Multimodal Multi‑Agent Framework Achieves High Accuracy in Ransomware Family ClassificationResearchers introduced a multimodal multi‑agent ransomware analysis framework that classifies ransomware families with high accuracy, evaluated on large‑scale datasets containing…