AI Synergies

Speakers

Jonathan Peck

PhD student

Calibrated Multi-Probabilistic Prediction as a Defense against Adversarial Attacks

We propose the MultIVAP, a scalable technique for hedging the predictions of any machine learning classifier. The algorithm incurs a reasonably small computational overhead and is able to significantly increase the robustness of the underlying model to adversarial perturbations without sacrificing accuracy. This increase in robustness is experimentally confirmed against defense-oblivious attacks as well as a white-box attack specifically designed for the MultIVAP.

Biography

Jonathan Peck received the B.Sc. degree in Computer Science and M.Sc. in Mathematical Informatics at Ghent University, Belgium, in 2015 and 2017 respectively. He is currently pursuing a Ph.D. at Ghent University, sponsored by a fellowship of the Research Foundation Flanders (FWO). His research focuses on improving the robustness of machine learning models to adversarial manipulations.


Program

Halle vitree
Research presentations AI
Day 3 - Nov 8th

Brewery of Ideas

AI Synergies is organized by VUB/ULB, BNVKI and Brewery of Ideas.

More info about our events