Technical Program

AML-P.1: Adversarial Machine Learning II

Symposium: Signal Processing for Adversarial Machine Learning
Session Type: Poster
Time: Thursday, November 29, 15:50 - 17:20
Location: Sleeping Beauty Pavilion
Session Chairs: Sijia Liu, IBM and Pin-Yu Chen, IBM Research AI
 
Poster Board: 1
AML-P.1.1: MULTI-VIEW FRAME RECONSTRUCTION WITH CONDITIONAL GAN
         Tahmida Mahmud; University of California, Riverside
         Mohammad Billah; University of California, Riverside
         Amit Roy-Chowdhury; University of California, Riverside
 
Poster Board: 2
AML-P.1.2: REINFORCED ADVERSARIAL ATTACKS ON DEEP NEURAL NETWORKS USING ADMM
         Pu Zhao; Northeastern University
         Kaidi Xu; Northeastern University
         Tianyun Zhang; Syracuse University
         Makan Fardad; Syracuse University
         Yanzhi Wang; Northeastern University
         Xue Lin; Northeastern University
 
Poster Board: 3
AML-P.1.3: IS ORDERED WEIGHTED L1 REGULARIZED REGRESSION ROBUST TO ADVERSARIAL PERTURBATION? A CASE STUDY ON OSCAR
         Pin-Yu Chen; IBM Research AI
         Bhanukiran Vinzamuri; IBM Research AI
         Sijia Liu; IBM Research AI
 
Poster Board: 4
AML-P.1.4: ZEROTH-ORDER STOCHASTIC PROJECTED GRADIENT DESCENT FOR NONCONVEX OPTIMIZATION
         Sijia Liu; IBM Research
         Xingguo Li; University of Minnesota
         Pin-Yu Chen; IBM Research
         Jarvis Haupt; University of Minnesota
         Lisa Amini; IBM Research
 
Poster Board: 5
AML-P.1.5: ON THE TRADEOFF BETWEEN MODE COLLAPSE AND SAMPLE QUALITY IN GENERATIVE ADVERSARIAL NETWORKS
         Sudarshan Adiga; University of Arizona
         Mohamed Adel Attia; University of Arizona
         Wei-Ting Chang; University of Arizona
         Ravi Tandon; University of Arizona
 
Poster Board: 6
AML-P.1.6: RANDOM ENSEMBLE OF LOCALLY OPTIMUM DETECTORS FOR DETECTION OF ADVERSARIAL EXAMPLES
         Amish Goel; University of Illinois at Urbana–Champaign
         Pierre Moulin; University of Illinois at Urbana–Champaign