場所：東京都のイベント

Seminar by Shpresim Sadiku (Zuse Institute Berlin) on \\"Minimally Distorted Interpretable Adversarial Attacks\\"

イベント説明

Speaker
Shpresim Sadiku (Technische Universität Berlin & Zuse Institute Berlin)
Title
Minimally Distorted Interpretable Adversarial Attacks
Abstract
Sparse adversarial attack approaches can be unified in a framework that is often based on a convex relaxation of the domain of the generated perturbation. However, there is a priori no real need for convexity relaxation. We consider generating adversarial images with a non-convex loss in a non-convex ℓp neighbourhood of an input image, thus stepping away from the ℓ0 combinatorial problem while remaining as continuous but sparser than the ℓ1 ball. We formalise the concept of finding adversarial examples as an explicit optimization problem for the special case of p = 1/2, for which we have access to an efficient proximal operator. In order to enhance the interpretability of generated attacks, we adjust the regularization parameter of the perturbation for each pixel separately. This modification increases the likelihood of perturbing pixels that are in proximity to the already perturbed pixels. Experiments show that our method computes highly sparse and interpretable adversarial examples for ImageNet models.
Zoom link
Time: Aug 28, 2023 10:45 AM Osaka, Sapporo, Tokyo
Join Zoom Meeting
https://riken-jp.zoom.us/j/98897491464?pwd=UUF6dkRUTW9TL0EzeWpickNDMy9idz09
Meeting ID: 988 9749 1464
Passcode: 4LhxeEKUii
Speaker's bio
Shpresim Sadiku is a PhD candidate at the Institute of Mathematics, Technische Universität Berlin, working under the supervision of Prof. Dr. Sebastian Pokutta. He is also affiliated with the Interactive Optimization and Learning (IOL) research lab at the Zuse Institute Berlin, where he holds a Scientific Assistant position. Previously, he worked on Neural Ordinary Differential Equations and Neural Networks Approximation Theory. He received an MSc in Mathematics in Data Science under the supervision of Prof. Dr. Michael Wolf at the Technical University of Munich in May 2020 and a BSc in Mathematics at the University of Tirana in July 2017.
His current research interests lie at the interface of 2D Computer Vision and Optimization, with a primary focus on developing efficient adversarial attack and defense techniques for deep neural networks. Currently, he is using first-order optimization methods to generate sparse adversarial attacks of high visual quality.
Host
Minh Ha Quang (Functional Analytic Learning Team, RIKEN-AIP)

開催日

2023年8月28日11:00 ～ 2023年8月28日12:30

主催者・問い合わせ先

RIKEN AIP Public

開催場所

項目内容
場所名称未設定
住所Open space at AIP Nihonbashi and via Zoom

開催場所の地図

SNS・Bookmark

B!

近隣のイベント

近隣の場所 (直線距離)