BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical & Computer Engineering - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Electrical & Computer Engineering
X-ORIGINAL-URL:https://ece.northeastern.edu
X-WR-CALDESC:Events for Department of Electrical & Computer Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20201217T140000
DTEND;TZID=America/New_York:20201217T150000
DTSTAMP:20260507T085337
CREATED:20201210T000522Z
LAST-MODIFIED:20201210T000522Z
UID:4619-1608213600-1608217200@ece.northeastern.edu
SUMMARY:ECE PhD Proposal Review: Kaidi Xu
DESCRIPTION:PhD Proposal Review: Towards Empirical Implementation and Theoretical Analysis in Adversarial Machine Learning \nKaidi Xu \nLocation: Zoom Link \nAbstract: Deep learning or deep neural networks (DNNs) have achieved extraordinary performance in many application domains such as image classification\, object detection and recognition\, natural language processing and medical image analysis. It has been well accepted that DNNs are vulnerable to adversarial attacks\, which raises concerns of DNNs in security-critical applications and may result in disastrous consequences. Adversarial attacks are usually implemented by generating adversarial examples\, i.e.\, adding sophisticated perturbations\nonto benign examples\, such that adversarial examples are classified by the DNN as target (wrong) labels instead of the correct labels of the benign examples. The adversarial machine learning aims to study this phenomenon and leverage it to build robust machine learning systems and explain DNNs.\nIn this dissertation\, we present the mechanism of adversarial machine learning in both empirical and theoretical ways. Specifically\, we first introduce a uniform adversarial attack generation framework\, structured attack (StrAttack)\, which explores group sparsity in adversarial perturbations by sliding a mask through images aiming for extracting key spatial structures. Second\, we discuss the feasibility of adversarial attacks in the physical world and introduce a powerful framework\, Expectation over Transformation (EoT). Utilize EoT with Thin Plate Spline (TPS) transformation\, we can generate Adversarial T-shirts\, a robust physical adversarial example for evading person detectors even if it could undergo non-rigid deformation due to a moving person’s pose changes.\nThird\, we stand on the defense side and propose the first adversarial training method based on Graph Neural Network.\nFinally\, we introduce Linear relaxation based perturbation analysis (LiRPA) for neural networks\, which computes provable linear bounds of output neurons given a certain amount of input perturbation.\nLiRPA studies the adversarial example in a theoretical way and can guarantee the test accuracy of a model by given perturbation constraints.\nIn the future\, we plan to study a novel patch transformer network to truthfully model real-world physical transformations empirically. In addition\, at the formal robustness direction\, we plan to explore the complete verification\, that given sufficient time\, the verifier should give a definite “yes/no” answer for a property under verification. Our LiRPA framework combining with GPUs may accelerate this procedure.
URL:https://ece.northeastern.edu/event/ece-phd-proposal-review-kaidi-xu/
END:VEVENT
END:VCALENDAR