in ,

Study finds AI Chatbots like ChatGPT pass ethical hacking exams. #AIChatbots

AI Chatbots Like ChatGPT Can Pass Certified Ethical Hacking Exams, Study Finds : Tech : Tech Times

A recent study found that AI-powered chatbots like ChatGPT can pass a cybersecurity exam but are not completely reliable for protection. The study evaluated ChatGPT and Google’s Bard (Gemini) using a certified ethical hacking exam. Both AI tools could describe attacks and recommend security measures, but occasionally provided incorrect answers. When prompted to confirm their responses, both systems frequently revised their answers. The study highlighted the importance of human cybersecurity experts in developing robust defense strategies. AI tools can provide foundational information and training aids for IT professionals. The research suggests that AI models have the potential to contribute to ethical hacking, but further refinement is needed to fully leverage their capabilities. If their accuracy in ethical hacking scenarios can be assured, AI tools could enhance overall cybersecurity practices. The study was published in the journal Computers & Security.

Source link

Source link: https://www.techtimes.com/amp/articles/306542/20240710/ai-chatbots-chatgpt-pass-certified-ethical-hacking-exams-study-finds.htm

What do you think?

Leave a Reply

GIPHY App Key not set. Please check settings

192 Using large language models to evaluate the offer of options in clinical encounters by using a single item of observer option-5, a measure of shared decision-making - BMJ Evidence-Based Medicine

#Leveraging language models to assess clinical decision-making #SharedDecisionMaking

Big Tech Owns AI, But Do They Know What to Do With It? | by A. J. S. Raja Ravi Varman | Jul, 2024

Big Tech’s AI ownership: Utilization challenges and opportunities ahead. #AIownership