Results for “"mode"”
41–50 of 1,668 articles
Best match · title matches first
The Register
2 months ago
Claude Mythos only model to complete full cyber kill chain, experts say
Cyber Weapon Index finds AI attacks 'imminent'
ransomware hospital — both words
"data breach" — exact phrase
malware -android — exclude a word
(apple OR microsoft) patch — either company, plus patch
ransom* — a wildcard match
Searches article titles, summaries, keywords and sources. Filters use publication dates.
41–50 of 1,668 articles
Best match · title matches first
The Register
Cyber Weapon Index finds AI attacks 'imminent'
The Hacker News
Google on Wednesday announced Gemini 3.8 Flash Cyber, which it described as its most capable cybersecurity model, and has made it available to a set of trusted defenders via a new initiative called the Fairwind Program. "The Fairwind Program gives high-priority defenders (like governments, healthcare providers, and telecommunications services) early access to advanced models that help them
The Hacker News
Forescout Research - Vedere Labs said it used Anthropic's Claude to port a working pre-authentication remote code execution (RCE) exploit from one WAGO programmable logic controller (PLC) to another, executing attacker-supplied ARM shellcode on live hardware. The exploit targets CVE-2021-31886, a stack-based buffer overflow in the Nucleus FTP server's handling of the USER command
Dark Reading
In one attack, threat actors stole an API key that ultimately led to the consumption of $600,000 in public AI model credits for the security nonprofit.
The Register
Security ... this time it will be different
Dark Reading
OpenAI's Hugging Face attack postmortem shows agents don't care about rules — they need strong controls.
The Hacker News
Oasis Security has disclosed a weakness in NVIDIA NemoClaw that could let an attacker-controlled webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden instructions inside the model itself. The findings were shared with The Hacker News ahead of publication, and the report says Oasis Security reported them to NVIDIA's Product Security Incident
The Hacker News
Marimo has addressed a high-severity security flaw in its notebook software that allowed an attacker to execute an attacker-supplied Model Context Protocol (MCP) command in a specially crafted notebook, according to VulnCheck's CVE Numbering Authority (CNA) record. The CNA record says the command can run as a local subprocess when the notebook is opened in edit mode. The vulnerability, tracked
Dark Reading
Katie Moussouris of Luta Security talks with the Dark Reading News Desk about how enterprises will now need to monitor risks posed by their own agents in the wake of the recent Hugging Face attack.
Dark Reading
Researchers found that by combining two vulnerabilities, they could take over an Android device by delivering a payload and getting the victim to answer their phone.