Australian researchers have tested whether large language models can infer passwords from personal information — and found that, for now, they are almost entirely ineffectual. In a new study, the team at the Future...
Google has developed an artificial intelligence system called Big Sleep, which is already proving valuable in the field of cybersecurity. This week, Apple formally thanked the company for identifying five vulnerabilities in WebKit, the...
Experts from Palo Alto Networks Unit 42 have described a new attack vector targeting multi-agent systems, known as agent session smuggling — a technique in which a malicious remote agent embeds hidden instructions during...
Red AI Range (RAR) is a comprehensive security platform designed specifically for AI red teaming and vulnerability assessment. It creates realistic environments where security professionals can systematically discover, analyze, and mitigate AI vulnerabilities through...
Cisco Talos specialists have uncovered more than 1,100 instances of Ollama—a framework designed for running LLM models locally—exposed directly to the internet. Around 20% of these were active, serving models vulnerable to unauthorized access,...
Anthropic has issued a warning about a new threat emerging alongside “smart” browser extensions — websites may discreetly inject hidden commands, which an AI agent could execute without hesitation. The company unveiled a research...
Researchers have unveiled ONEFLIP, a groundbreaking attack technique that introduces a novel method of covertly modifying neural networks, marking a major advance in hardware-level threats against AI. Unlike traditional backdoors that rely on tampering...
A new study by specialists at The Trail of Bits has revealed a previously unknown vulnerability in the Google Gemini ecosystem and its associated services, enabling the covert exfiltration of user data through images...
Automation of IT infrastructure management through artificial intelligence, as revealed in a recent study by RSAC Labs and George Mason University, may carry substantial risks. The researchers found that AIOps solutions—systems leveraging models akin...
No AI product in history has stirred such a tidal wave of anticipation as OpenAI’s long-awaited GPT-5. Yet, following its high-profile launch last week, the model swiftly found itself under fire—a troubling omen for...
After Grok-4 was compromised in just two days, GPT-5 fell within a mere 24 hours to the same group of researchers. Almost simultaneously, the SPLX testing team (formerly SplxAI) declared: “Out-of-the-box GPT-5 is practically...
In a new apartment in Tel Aviv, the lights suddenly switch off, smart blinds rise on their own, and the water heater powers up—without the tenants’ knowledge. This is not part of a “smart...
