The rapid adoption of artificial intelligence tools is raising new security concerns worldwide.
The U.K.’s National Cyber Security Centre is warning against the use of large language models supporting popular AI tools such as ChatGPT since they could be involved in cyberattacks.
“An attacker might be able [to] send a user a transaction request, with the transaction reference hiding a prompt injection attack on the LLM,” the cyber official wrote. “When the user asks the chatbot, ‘Am I spending more this month?’ the LLM analyzes transactions, encounters the malicious transaction and has the attack reprogram it into sending users’ money to the attacker’s account.”
Employees reportedly asked the chatbot to generate minutes from a recorded meeting and to check sensitive source code after Samsung’s semiconductor division let its employees use the new AI tools. AI rules crafted by China are likely to be frowned on by U.S. officials worried about intellectual property theft and fretting that the communist government doesn’t share American values surrounding free digital discourse.
France Dernières Nouvelles, France Actualités
Similar News:Vous pouvez également lire des articles d'actualité similaires à celui-ci que nous avons collectés auprès d'autres sources d'information.
British officials say AI chatbots could carry cyber risksBritish officials are warning organisations about integrating artificial intelligence-driven chatbots into their businesses, saying that research has increasingly shown that they can be tricked into performing harmful tasks.
Lire la suite »
Auto Industry Struggling With Creating A Cyber TrustThe trust required throughout the system is multi-layered and complex: the developer trust, the ecosystem trust, and the buyer’s trust. And at least one has no solution.
Lire la suite »
Feds take down a botnet responsible for ransomware attacks, including a Southern California food distributorThe takedown represents the largest United States-led financial and technical disruption of a botnet infrastructure leveraged by cybercriminals to commit cyber-enabled criminal activity.
Lire la suite »
Businesses Warned Over Risks Of Chatbot Prompt Injection AttacksBusinesses should be very cautious when integrating large language models (LLMs) into their services, the UK's National Cyber Security Centre (NCSC) is warning, thanks...
Lire la suite »
Goldman Sachs used Chinese state funds to buy US, UK firms: reportGoldman used cash from a sovereign wealth fund to buy seven companies, including a cyber security firm that services the British government.
Lire la suite »
Orsted shares drop after offshore wind group warns of impairments risk By Investing.comOrsted shares drop after offshore wind group warns of impairments risk
Lire la suite »