Subscribe to our channel: https://youtube.pl/c/DevoxxPoland?sub_confirmation=1
2023 will be known as the year of AI was launched into an unprepared world. AI has changed the safety scenery in many areas, from next-gen phishing emails to AI-powered script kiddies. In this presentation, we demo how hackers and red teamers are utilizing AI to their advantage.
1 What is AI
We will research how AI models are trained, including looking at the most common training set, the ‘Common Crawl Database’ and why generative AI can consume trash, yet inactive sound convincing in their answers. We will besides dive into the different types of AI specified as LLMs vs generative AI, predictive AI, and contextual AI.
2 AI in the incorrect hands
We show how malicious actors can usage AI tools for nefarious activities including abusing AI dependency hallucinations, data poising, and utilizing prompt injection to get to the hidden treasures of an AI model. We besides look at the concerns of open-source AI models which can be adapted to give script kiddies super powers.
3 utilizing AI safely
During this section, we will discuss any of the many ways AI can be utilized to aid developers without destroying security
4 Conclusion
AI is neither good nor bad, but it is here to stay. By reviewing how malicious actors usage AI, the risks that come with it, and the benefits it brings, this endurance guide will aid any developer, hacker or defending build for and with AI.
Recorded at Devoxx Poland 2024
Twitter: https://twitter.com/DevoxxPL
Instagram: https://www.instagram.com/DevoxxPL
Join us besides here:
Devflix: https://devflix.pl
#Devoxx #DevoxxPoland #IT #Development #SoftwareDevelopment
