Dark Reading Articles

Updated 2 min ago · 10 articles from Dark Reading

Dark Reading Sep 4, 12:15 PM

Insurers Search for Answers to Rein in Rogue AI

As incidents of unintended harm caused by rogue AI agents mount, CISOs and insurance firms are figuring out how to handle the fallout.

Dark Reading Sep 3, 2:38 PM

AI 'Machine Speed' Cuts 2-Week Attack Down to 10 Hours

The incident demonstrates how frontier AI agents can dramatically compress an attack timeline and coordinate a large-scale breach, according to researchers.

Dark Reading Aug 31, 9:08 PM

Anthropic Users Hit by Infostealer Attacks, Session Thefts

A threat actor used a variety of infostealers to collect session information and access Claude accounts belonging to an unknown number of users.

Dark Reading Aug 31, 5:34 PM

AI Model Rules Are Not Security Controls

OpenAI's Hugging Face attack postmortem shows agents don't care about rules — they need strong controls.

Dark Reading Aug 28, 8:19 PM

Hundreds of OpenAI Agents Invaded Hugging Face Servers

The Hugging Face incident was bigger and worse than previously thought, with approximately 700 agents collaborating on a sophisticated, multistage attack.

Dark Reading Aug 28, 1:30 PM

Defining an AI Kill Switch Is Hard, but Necessary

Proposed legislation could mandate that companies be able to "throttle, suspend, or shut ... down" AI agents, but how and when to do that remain open questions.

Ad
Dark Reading Aug 28, 1:00 PM

The Vulnpocalypse Is Repricing the Bug Bounty Economy

The surge in AI-powered vulnerability reports is driving down bug bounty prices, and that could spell trouble for independent researchers.

Dark Reading Aug 26, 7:54 PM

'HTTP Terminator' Hunts for Novel Desync Attacks

James Kettle of PortSwigger talks with the Dark Reading News Desk about his AI-powered open source tool, which found new HTTP request-smuggling techniques.

Dark Reading Aug 25, 9:08 PM

Hidden Prompts Trick AI Into False Email Summaries

With some simple HTML that's invisible to users, attackers can manipulate AI-powered email summarizers into producing malicious information.

Dark Reading Aug 25, 7:50 PM

Finding Nemo(Claw): Networking Issue Allows for LLM Poisoning in OpenClaw

Attackers can exploit a security bug in Nvidia's tool to gain unauthenticated access to the local model server through the Ollama API, paving the way for per...