U.S. Commerce Sec. Lutnick says American AI dominates DeepSeek, thanks Trump for AI Action Plan
The attack was allegedly conducted in five phases — in Phase 1, the human operator assigns a target to Claude. In Phase 2, the AI is instructed to conduct its initial reconnaissance, using scan, search, data retrieval, and code analysis tools to deliver an initial analysis and summary of the target to its operator. Phase 3 is a more targeted version of Phase 2, where the AI runs a vulnerability scan based on its findings to determine how it will compromise the target.
This is also where the operator can instruct the AI to begin exploitation by engaging callback services. Again, the human operator reviews the AI’s findings and may even give the tool additional directives, either to run the scan again and find more weaknesses in the network or to begin Phases 4 and 5. In the last phases of the attack, the human operator directs the AI tool to obtain credentials and access data. At these stages, both the human and the AI tool can use the exploitation tools to locate and exfiltrate data from the target.
Although the AI still reverts to the human operator in various steps of the network intrusion, it mostly does this to report its findings and for further instructions. Otherwise, it mostly runs independently, around 80% to 90% of the time, allowing the bad actors to run an elaborate operation much quicker and with fewer humans in the loop.
Anthropic says that Claude has built-in safeguards to help prevent this from happening, but the attackers were able to circumvent this. The first thing they did was to convince the LLM that it was working for a cybersecurity company, and that it was being used for penetration testing and red teaming. They also broke down the entire operation into smaller, seemingly innocent tasks. This prevented Claude from seeing the entire context of the operation and the true purpose of its instructions.
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/cyber-security/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/cyber-security/anthropic-says-it-has-foiled-the-first-ever-ai-orchestrated-cyber-attack-originating-from-china-company-alleges-attack-was-run-by-chinese-state-sponsored-group#main
- https://www.tomshardware.com
- Hands-on with Valve's new Steam Frame headset — Arm-powered, mixed-mode device uses Fex translation layer for traditional x86 games
- Microsoft patches Windows 10 issue that accidentally blocked extended security updates from installing — latest update should finally fix all the issues for ESU
- Google strikes massive deal to buy 1.5 terawatt hours of Ohio solar capacity — 15-year deal will see most of 50 megawatt solar farm's capacity diverted to data
- AMD's gaming-optimized Ryzen 5 7500X3D with 96 MB of 3D V-Cache shows up in UK stores — here's where to buy AMD's latest budget X3D chip
- Best Motherboard Deals 2025 – deals on Intel and AMD motherboards
Informational only. No financial advice. Do your own research.