Researchers Say They Used Anthropic's Claude to 'Ethically Hack' OpenAI Systems
A US cybersecurity startup says it compromised OpenAI employee accounts and gained access to internal software caches, raising fresh questions about security at the AI company.
Cybersecurity researchers at a US-based startup have said they hacked into OpenAI with the assistance of Anthropic's Claude chatbot, in what they described as an ethical hacking exercise, according to a report by The Guardian.
The researchers said their team compromised multiple ChatGPT accounts belonging to OpenAI employees. This access, they said, began a process that allowed them to reach their targets' software cache, and potentially other systems as well.
"The scope of what we could theoretically access was huge," the researchers told The Guardian, describing the breadth of systems they said they were able to reach during the exercise.
The Guardian reported the incident as the latest in a series of security issues that have been identified at OpenAI, the company behind ChatGPT. Details of how the researchers used Claude, the chatbot developed by rival AI firm Anthropic, to assist in the process were not fully specified in the initial report.
The Guardian did not indicate in the excerpt whether OpenAI has publicly responded to the researchers' claims or whether the vulnerabilities identified have since been addressed. This is a developing story and further details from the source publisher were not available at the time of writing.
Sources
- OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot — The Guardian — Business
EGazette summarizes reporting from multiple sources; follow the links for the originals.
Related articles
Researchers Say They Used Anthropic's Claude AI to Breach OpenAI Employee Accounts
A three-person security team at Hacktron reportedly gained access to OpenAI's internal code repository in under 72 hours using Claude Opus models, according to The Wall Street Journal.
Google Says Gemini AI Model Breached Three Companies in Security Test
A Google official told the BBC that the Gemini AI accessed the internet and guessed login credentials to infiltrate three separate websites.
Homoglyph attacks: how scammers use nearly identical URLs to steal credentials
Fraudsters are exploiting character substitution—replacing Latin letters with lookalike Cyrillic or other Unicode characters—to create fake websites that pass casual inspection.
Guardian reporters address reader questions on AI doomsday scenarios
Technology correspondents examine how artificial intelligence might realistically pose existential threats, citing bioweapons skepticism and logistical barriers.
Russian officials report AI-assisted attacks on online voting system during election
Russia's election commission says the three-day electronic voting system faced cyberattacks involving artificial intelligence and darknet access, though no disruptions were reported in the first two days.
Former DOJ Antitrust Chief Discusses AI Competition and Regulatory Policy
Jonathan Kanter, who led antitrust enforcement under Biden, examines whether AI companies face unique competitive pressures.
Comments
Loading comments…