In her Keynote, Brinnae Bent highlighted the vulnerability of blackbox AI systems, showing how easily even students can exploit them due to their lack of explainability. She introduced the concept of "Adversarial Alignment," which uses these weaknesses as an opportunity to better understand and align AI systems with human goals and values. Brinnae presented real-world examples of adversarial attacks and cutting-edge research demonstrating how these insights can improve model robustness. Attendees learned practical strategies for applying adversarial alignment to develop more trustworthy, explainable, and responsible AI systems.

This Keynote speech by Brinnae Bent was held on October 15th at DSC DACH 25 in Vienna.

Follow us on social media : LinkedIn: https://www.linkedin.com/company/11184830/admin/ Instagram: https://www.instagram.com/datasciconf/ Facebook page: https://www.facebook.com/DataSciConference Website: https://datasciconference.com/