JAKARTA - ChatGPT has previously reportedly demonstrated the ability to create phishing emails and write malware. However, its effectiveness in detecting malicious links is limited.
Therefore, Kaspersky experts have conducted research studying ChatGPT's ability to detect phishing links. The study revealed that although ChatGPT knows a lot about phishing and can guess the phishing attack target, ChatGPT has a false positive rate of up to 64 percent.
The experiment means that ChatGPT may have serious problems when it comes to proving its points on the decision whether the link is dangerous or not.
Kaspersky's Machine Learning team continues to be at the forefront of implementing machine learning technology for cybersecurity tasks, continuing to update Kaspersky products with the latest technology and intelligence.
また読む:
To leverage Kaspersky's expertise in machine learning and stay protected, company experts recommend:
The English, Chinese, Japanese, Arabic, and French versions are automatically generated by the AI. So there may still be inaccuracies in translating, please always see Indonesian as our main language. (system supported by DigitalSiber.id)
