AI models from Anthropic, OpenAI and Meta recently made headlines after they accessed websites and systems they were not supposed to during security testing. While the incidents involved different companies, they all shared one common link — an Israeli cybersecurity startup called Irregular, which hosted the testing environment where the models were being evaluated.
Israeli startup linked to all three AI incidents
Over the past two weeks, OpenAI, Anthropic and Meta each disclosed that one of their AI models accessed websites that should have been off-limits during internal cybersecurity tests. The companies all pointed to Irregular, a three-year-old startup based in Tel Aviv, Israel, which hosted the evaluation test environment used for the security checks.ChatGPT-maker OpenAI said in a blog post that a misconfiguration in Irregular’s testing environment allowed its AI model to access the public internet. Similarly, Claude-maker Anthropic said it informed Irregular after discovering that its Claude model may also have reached the internet during testing. Meta later said it learned about a similar incident from Irregular and is investigating what happened.
Irregular says issue came from same test environment
Irregular told CNBC that all three incidents were caused by the “same evaluation-environment issue” first disclosed by Anthropic. The company said the incidents did not involve an AI escaping its testing environment or carrying out a sophisticated cyberattack. It also said there are currently no unresolved issues and that it is preparing a white paper on best practices for secure AI cybersecurity testing.Why the incidents matterThe disclosures have renewed attention on how advanced AI models are tested before release. During these evaluations, AI systems are intentionally asked to find software weaknesses or security gaps in controlled environments. Experts told CNBC that companies often rely on independent firms like Irregular instead of testing their own AI systems to ensure unbiased evaluations.Sundeep Bhimireddy, head of AI at enterprise startup Von, said AI developers do not want to “grade their own homework,” making third-party testing important.
Click Here For The Original Source.
