Artificial intelligence (AI) tools such as ChatGPT can be tricked into producing malicious code which could be used to launch cyber attacks, according to research. A study by researchers from the University of Sheffield’s Department of Computer Science found that it was possible to manipulate chatbots into creating code capable of breaching other systems. Generative AI tools such as ChatGPT can create content based on user commands or prompts and are expected to have a substantial impact on daily life as they become more widely used in industry, education and healthcare. But the researchers have warned that vulnerabilities exist, and said their research found they were able to trick the chatbots into helping steal sensitive personal information, tamper with or destroy databases, or bring down services using denial-of-service attacks. In reality many companies are simply not aware of these types of threats and due to the complexity of chatbots, even within the community, there are things that are not fully understood Xutan Peng, University of Sheffield PhD student In all, the university study found vulnerabilities in six commercial AI tools – of which ChatGPT was the most well-known. On Chinese platform Baidu-Unit, the scientists were able to use malicious code to obtain confidential Baidu server configurations and tampered with one server node. In response, the research has been recognised by Baidu, which addressed and fixed the reported vulnerabilities and financially rewarded the scientists, the university said. Xutan Peng, a PhD student at the University of Sheffield, who co-led the research, said: “In reality many companies are simply not aware of these types of threats and due to the complexity of chatbots, even within the community, there are things that are not fully understood. “At the moment, ChatGPT is receiving a lot of attention. It’s a standalone system, so the risks to the service itself are minimal, but what we found is that it can be tricked into producing malicious code that can do serious harm to other services.” The risk with AIs like ChatGPT is that more and more people are using them as productivity tools, rather than a conversational bot, and this is where our research shows the vulnerabilities are Xutan Peng, University of Sheffield PhD student The researchers also warned that people using AI to learn programming languages was a danger, as they could inadvertently create damaging code. “The risk with AIs like ChatGPT is that more and more people are using them as productivity tools, rather than a conversational bot, and this is where our research shows the vulnerabilities are,” Peng said. “For example, a nurse could ask ChatGPT to write an (programming language) SQL command so that they can interact with a database, such as one that stores clinical records. “As shown in our study, the SQL code produced by ChatGPT in many cases can be harmful to a database, so the nurse in this scenario may cause serious data management faults without even receiving a warning.” The UK will host an AI Safety Summit next week, with the Government inviting world leaders and industry giants to come together to discuss the opportunities and safety concerns around artificial intelligence. Read More Tinder adds Matchmaker feature to let friends recommend potential dates Google and Meta withdraw from upcoming Web Summit ‘Game-changing’ facial recognition technology catches prolific shoplifters Facial recognition firm Clearview AI overturns UK data privacy fine Sadiq Khan, Met Commissioner to ask phone companies to ‘design out’ theft Microsoft gets go-ahead to buy Call of Duty maker Activision

X/Twitter owner Elon Musk says he's still down to have an actual, physical, non-metaphorical cage

The Pentagon will withhold about 10% of the price for new F-35s from Lockheed Martin Corp. until the

From developing his own Squid Game to giving out thousands of dollars to complete strangers, MrBeast has done it all

COP28 Daily Reports: Sign up for the Green Daily newsletter for comprehensive coverage of the climate summit right

Do you, like so many people, use Google Calendar for your personal life and Microsoft

Free trade negotiations between the UK and the six members of the Gulf Cooperation Council are “progressing well”

Are you still advertising on X, the Elon Musk-owned social media platform formerly known as

DraftKings is giving new users a guaranteed $200 bonus on any $5 Week Zero parlay bet! Find out how to claim this exclusive offer here.

DALLAS--(BUSINESS WIRE)--Sep 11, 2023--

The Fortnite Becky Lynch and Bianca Belair skins are now available for purchase, along with matching Back Blings and Pickaxes, for 2,400 V-Bucks.

Criminals are exploiting the analogue to digital switchover in the UK’s telephone network to scam elderly and vulnerable people, councils have warned. The Local Government Association (LGA) said it had issued the warning after becoming concerned the transition was creating new opportunities for scammers. Specifically, the LGA said it was concerned about the around 1.8 million people who use healthcare telephony devices, and which may need changing as part of the digital switchover. It said it had seen recent reports of scammers who call residents with healthcare devices and claim the resident needs to hand over bank details as part of the switchover, or they will be disconnected. As the digital switchover date approaches, sadly we fear that further cases will arise Councillor Heather Kidd, from the LGA The digital switchover will see most UK telephone providers move their customers from old analogue landlines to new, upgraded services which use digital technology, with the changes taking place up to 2025. Councillor Heather Kidd, chair of the LGA’s safer and stronger communities board, said: “We are very concerned by a rise in criminals taking advantage of the digital switchover to trick vulnerable residents into giving out personal information such as their bank details. “As the digital switchover date approaches, sadly we fear that further cases will arise. “Councils will always act swiftly with the police where any incidents are reported, but we also urge people to be vigilant and help to raise awareness of this crime. “The digital switchover is free of charge and residents should be aware that councils and their home care alarm providers or contractors will never ask for personal or financial information over the phone.” The LGA said anyone who is the victim of a scam or fraudulent activity should report it to Action Fraud as well as their local trading standards team. Read More Charity boss speaks out over ‘traumatic’ encounter with royal aide Ukraine war’s heaviest fight rages in east - follow live