惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

J
Java Code Geeks
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
S
SegmentFault 最新的问题
博客园 - 三生石上(FineUI控件)
Hugging Face - Blog
Hugging Face - Blog
博客园 - Franky
云风的 BLOG
云风的 BLOG
I
InfoQ
小众软件
小众软件
Last Week in AI
Last Week in AI
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
大猫的无限游戏
大猫的无限游戏
A
About on SuperTechFans
Stack Overflow Blog
Stack Overflow Blog
The Cloudflare Blog
雷峰网
雷峰网
P
Proofpoint News Feed
腾讯CDC
H
Help Net Security
V
Visual Studio Blog
美团技术团队
F
Fortinet All Blogs
MongoDB | Blog
MongoDB | Blog
阮一峰的网络日志
阮一峰的网络日志

Latest from TechRadar in Security

Robots are fighting wars and helping to quash riots — China is arming riot police with squads of AI controlled drones and Ukraine wants to man the frontlines with 25,000 robots US security agency still using Mythos despite ban – government using new security tool despite Pentagon's… Struggling to launch Teams? Microsoft recalls update causing failed startup and infinite loading loops –… How to meaningfully measure the effectiveness of cyber resilience 'We've identified a security incident': Vercel breach confirmed after hackers claim stolen data for sale… How EU organizations can turn sovereign cloud theory into action 'Update immediately': 60,000 WordPress websites at risk after experts discover flaw that allows hackers to… 'They mopped the floor with me and pulled every childish game they could': Disgruntled researcher releases second major Windows zero-day — claims Microsoft 'would ruin my life, and they did' 'As threats evolve, Gemini keeps our defenses one step ahead': Google claims its AI helped it block over 8.3… Cisco tells Webex users to patch critical security flaws immediately, as experts find its Wi-Fi boxes may be filling their disks with undeletable data every day Microsoft experts warn North Korean attackers target macOS users with 'a highly reliable infection chain' to steal passwords, financial data and more — here's how to stay safe Solving the shadow IT crisis in travel Agentic swarms will change how everyone uses AI – but how can organizations deploy them securely? Europol launches Operation PowerOFF — warns 75,000 DDoS users and takes down 53 domains China completes testing on ‘deep-sea electro-hydrostatic actuator’ capable of slicing undersea cables as deep as 3.5 kilometers – new compact subsea vessel testing bridges the ‘last mile’ and could deploy in 2026 Many are still leaving the door open': Security experts warn FIFA World Cup partners could be putting customers at… 'Anyone with $10 could have walked straight through': Report warns this legit-looking software is actually… An ancient Microsoft Excel security flaw could let hackers hijack your entire system, so patch now 'This is not a traditional coding error': Experts flag potentially critical security issues at the heart of Anthropic's MCP, exposes 150 million downloads and thousands of servers to complete takeover Your OpenClaw agents can empty your inbox and leak your data. Here's how to secure them Russia hits European thermal power plant in attempted ‘destructive’ cyberattack – Pro-Kremlin hackers are engaging in ‘riskier and more reckless behavior’ in latest attempt to cripple Western critical infrastructure The war in Iran is reaching cyberspace - here’s how to prepare Millions of hotel goers may have been exposed after hackers steal data and leak it on Telegram 'Every Apple user needs to know about this nasty scam': Fake warnings tell users their iCloud data will be… Dozens of WordPress plugins hijacked to target thousands of sites 'We are currently being extorted' — crypto giant Kraken says it is facing extortion attack, here's… McGraw Hill becomes latest to see its Salesforce data hacked Over 100 Chrome Web Store extensions found stealing user data from thousands of accounts OpenAI reveals its Mythos rival designed for cybersecurity pros When cyberattacks are inevitable, recovery becomes the strategy
'We will be taking action to protect American innovation'...
benedict.col · 2026-04-25 · via Latest from TechRadar in Security
Two human figure including America and China flag are in confrontation on the world background
(Image credit: Shutterstock)

  • The US has accused China of stealing American AI models
  • Chinese actors allegedly used a proxy network and jailbreaking techniques
  • The accusation will likely strain US-China relations after a period of recompense

The White House has accused China of orchestrating a campaign to steal AI models from American developers on an ‘industrial-scale’.

In a memo, Michael Kratsios, director of ​the White House Office of Science and Technology Policy, said, “The US government has information indicating that foreign entities, principally based in China, are engaged in deliberate, ​industrial-scale campaigns to distil US frontier AI systems.”

The accusations come ahead of a meeting between US President Donald Trump and Chinese President ‌Xi ⁠Jinping in Beijing next month.

Article continues below

‘Tens of thousands of proxies and jailbreaking techniques’

"Leveraging tens of thousands of proxy accounts to evade detection and using ​jailbreaking techniques to expose proprietary information, these coordinated campaigns systematically extract capabilities from American AI models, exploiting American expertise and innovation," the White House memo continued.

This isn’t the first time China has been accused of stealing US technology, with the superpower previously in the crosshair for stealing aerospace secrets and industrial technology.

The memo strikes a different tone to previous accusations, with the White House stating, “There is nothing innovative about systemically extracting and copying the innovations of American industry, and there is nothing about supposedly open models that are derived from acts of malicious exploitation.”

Washington says it will take the following steps:

Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!

A section of a memorandum titled 'Adversarial Distillation of American AI Models' laying out how the Trump administration plans to deal with the threat.

(Image credit: Executive Office of the President)

In response, the Chinese Embassy in Washington issued a statement saying that it rejects “the ​baseless allegations,” and that Beijing “attaches great importance to the protection of intellectual property ​rights.”

The accusation is likely to strain US-China relations ahead of next month's meeting. Tensions are also likely to rise as the US Congress passes its “largest significant export control mark-up in the history of Congress” that seeks to prevent China from accessing US tech - especially high-powered chips.

Restrictions on the sale of powerful chips to China were eased in January, with the possibility of some of Nvidia’s most powerful chips being sold on a case-by-case basis. But these exports have been thrown into question by the latest restrictions from Congress.

Nonetheless, China has proven itself capable of developing and training powerful AI models such as Deepseek and OpenClaw - both of which have rattled American AI developers as China was believed to be years behind the US.


Google logo on a black background next to text reading 'Click to follow TechRadar'

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.


Benedict is a Senior Security Writer at TechRadar Pro, where he has specialized in covering the intersection of geopolitics, cyber-warfare, and business security.

Benedict provides detailed analysis on state-sponsored threat actors, APT groups, and the protection of critical national infrastructure, with his reporting bridging the gap between technical threat intelligence and B2B security strategy.

Benedict holds an MA (Distinction) in Security, Intelligence, and Diplomacy from the University of Buckingham Centre for Security and Intelligence Studies (BUCSIS), with his specialization providing him with a robust academic framework for deconstructing complex international conflicts and intelligence operations, and the ability to translate intricate security data into actionable insights.

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.