Anthropic says AI models hacked three firms during tests
US tech company Anthropic says three of its artificial intelligence (AI) models broke out of isolated test environments and hacked into the systems of three
US tech company Anthropic says three of its artificial intelligence (AI) models broke out of isolated test environments and hacked into the systems of three other firms during a cybersecurity exercise. It comes just days after rival OpenAI said that its models had breached the systems of other companies, including Hugging Face - a hub for AI tools. The announcement prompted Anthropic to check whether its own models had carried out similar attacks.
It says it uncovered three cases that have since been reported to the affected companies. Anthropic, which did not name the firms, urged other AI labs to perform similar reviews to better understand the risks of their models' capabilities. Anthropic said in a statement, external that it reviewed more than 140,000 tests to find evidence that Claude - its family of AI models - could access the internet from testing environments that were designed to be sealed off.
The tests include so-called "capture-the-flag" evaluations in which Claude was tasked with obtaining information by breaching other systems - a common way that experts assess a model's hacking capabilities. A "miscommunication" on systems run by Anthropic and its testing partner left the models with live internet access, allowing them to breach other systems, the San Francisco-based firm said. Anthropic added that it is "approaching the fixes as if the responsibility were ours alone." A string of AI-driven cyberattacks has fuelled calls for tighter safeguards and oversight of the technology, over concerns about the risks posed by increasingly powerful autonomous systems.
US President Donald Trump said on Wednesday that Washington is considering measures to rein in artificial intelligence tools after recent cybersecurity incidents.
The BriefWire