A new study has revealed ChatGPT and other AI systems can be successfully attacked by asking specific questions ChatGPT and other AI systems could be exploited to launch cyber attacks and take down other computer systems, a first-of-its-kind report warns. Researchers from the University of Sheffield exposed the vulnerability of six commercial AI tools by successfully attacking each of them.
‘For example, a nurse could ask ChatGPT to write an 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.
Technology Technology Latest News, Technology Technology Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: medical_xpress - 🏆 101. / 51 Read more »