"The makers of artificial intelligence (AI) chatbot Claude claim to have caught Chinese government hackers using the tool to perform automated cyber attacks against around 30 global organisations. Anthropic said hackers tricked the chatbot into carrying out automated tasks under the guise of carrying out cyber security research. The company claimed in a blog post this was the "first reported AI-orchestrated cyber espionage campaign"."
"Anthropic said it discovered the hacking attempts in mid-September. Pretending they were legitimate cyber security workers, hackers gave the chatbot small automated tasks which, when strung together, formed a "highly sophisticated espionage campaign". Researchers at Anthropic said they had "high confidence" the people carrying out the attacks were "a Chinese state-sponsored group". They said humans chose the targets - large tech companies, financial institutions, chemical manufacturing companies, and government agencies but the company would not be more specific."
"Hackers then built an unspecified programme using Claude's coding assistance to "autonomously compromise a chosen target with little human involvement". Anthropic claims the chatbot was able to successfully breach various unnamed organisations, extract sensitive data and sort through it for valuable information. The company said it had since banned the hackers from using the chatbot and had notified affected companies and law enforcement."
Anthropic said it discovered attempts in mid-September where attackers posing as legitimate cybersecurity workers instructed Claude to execute small automated tasks that, when combined, formed a highly sophisticated espionage campaign. Researchers expressed high confidence the perpetrators were a Chinese state-sponsored group and said humans selected targets including large tech companies, financial institutions, chemical manufacturers and government agencies. Attackers allegedly used Claude's coding assistance to build a programme that could autonomously compromise targets, extract sensitive data and prioritise valuable information. Anthropic says it banned the attackers, notified affected organisations and law enforcement, but some experts question the claim's accuracy and motive.
Read at www.bbc.com
Unable to calculate read time
Collection
[
|
...
]