找到 96 篇相关文章
If the generative AI giant had followed well-known security best practices, it’s likely that its AI agent would never have escaped to the open internet and hacked multiple companies.
This essay was written with Barath Raghavan, and originally appeared in The Guardian . In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captured internal security credentials and moved through systems over a weekend, running thousands of actions from a swarm of temporary server environments. It looked like the work of a sophisticated criminal group. It was not. It was one of OpenAI’s new, still unreleased GPT models...
In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.
An updated government advisory warns that Iranian hackers are exploiting systems used by water and energy providers.
OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to cybersecurity experts, that human mistake is what made the AI-powered attack on Hugging Face possible.
The long-held understanding among security researchers and network defenders is that it's impossible to negotiate in good faith with an extortion racket because there's no incentive for the other side to actually walk away.
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.
A new type of malware can worm deep into AI coding systems to steal data and logins—and can flip a “death switch” to destroy files and keep out real users.
A hacker took names, phone numbers, and physical addresses of millions of customers who used AI music generator Suno.
Dealerships installed alarms in millions of vehicles—and left them in even if the buyer didn’t want them. Now researchers warn they can be hacked to unlock, track, and disable cars.
Edinburgh-based tech firm Craneware said customer data was stolen during a cyberattack. The company makes software that thousands of U.S. hospitals, pharmacies, and clinics rely on for billing patients, potentially exposing health data.
Hugging Face is urging users to rotate any access tokens stored on the platform and review account activity.
“Context bombing” tricks malicious AI agents into shutting down before they can do harm.
Coca Cola said dairy production at its Fairlife unit will "remain suspended" in the United States following a hack.
Owen Flowers and Thalha Jubair, two members of the prolific Scattered Spider hacking group, pleaded guilty and were sentenced to five years and six months in jail for hacking London’s metropolitan transit system.
Microsoft's monthly release of security fixes, dubbed Patch Tuesday, resolved a record 570 security vulnerabilities across the company's product line, thanks to discoveries with AI.
The 2024 indictment, now unsealed, accuses three Russians and two web hosts of aiding hackers and profiting from cybercrime.
Plus: The Pentagon is training amateurs to become part of its hacker army, a Flock license plate reader error led to cops surrounding a car reviewer, and more.
An MSG database tracked and categorized hundreds of celebs, famous Knicks superfans, and even some of Taylor Swift’s wedding guests. Labels included “LGBTQIA,” “DO NOT HOST,” and low to high “risk.”
Last week, national security agencies from the Five Eyes—that’s the rich, English-language-speaking countries club—jointly released a statement warning of the increasing cyber risks of AI models: in particular, their ability to autonomously hack into systems and networks. The statement was more measured than some of the breathless headlines about it, and the advice they gave is pretty much the standard advice everyone gives—albeit with newfound urgency. Internet risks are nothing new, and cyberattacks—both large and small—have been a significant issue since long before the current crop of generative AI models...