Microsoft Uncovers ‘Whisper Leak’ Attack That Identifies AI Chat Topics in Encrypted Traffic
Microsoft has disclosed details of a novel side-channel attack targeting remote language…
Researchers Uncover GPT-5 Jailbreak and Zero-Click AI Agent Attacks Exposing Cloud and IoT Systems
Cybersecurity researchers have uncovered a jailbreak technique to bypass ethical guardrails erected…
CERT-UA Discovers LAMEHUG Malware Linked to APT28, Using LLM for Phishing Campaign
Jul 18, 2025Ravie LakshmananCyber Attack / Malware The Computer Emergency Response Team…
Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data Without User Interaction
A novel attack technique named EchoLeak has been characterized as a "zero-click"…
Why LLMs Overthink Easy Puzzles but Give Up on Hard Ones
Artificial intelligence has made remarkable progress, with Large Language Models (LLMs) and…
AI Acts Differently When It Knows It’s Being Tested, Research Finds
Echoing the 2015 ‘Dieselgate' scandal, new research suggests that AI language models…
Large Language Models Are Memorizing the Datasets Meant to Test Them
If you rely on AI to recommend what to watch, read, or…
Using AI to Predict a Blockbuster Movie
Although film and television are often seen as creative and open-ended industries,…
Inside OpenAI’s o3 and o4‑mini: Unlocking New Possibilities Through Multimodal Reasoning and Integrated Toolsets
On April 16, 2025, OpenAI released upgraded versions of its advanced reasoning…