Search Results for author: Gaoyuan Zhang

Found 12 papers, 5 papers with code

Generating Realistic Physical Adversarial Examplesby Patch Transformer Network

no code implementations29 Sep 2021 Quanfu Fan, Kaidi Xu, Chun-Fu Chen, Sijia Liu, Gaoyuan Zhang, David Daniel Cox, Xue Lin

Physical adversarial attacks apply carefully crafted adversarial perturbations onto real objects to maliciously alter the prediction of object classifiers or detectors.

Fast Training of Provably Robust Neural Networks by SingleProp

no code implementations1 Feb 2021 Akhilan Boopathy, Tsui-Wei Weng, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Luca Daniel

Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees.

Distributed Adversarial Training to Robustify Deep Neural Networks at Scale

no code implementations1 Jan 2021 Gaoyuan Zhang, Songtao Lu, Sijia Liu, Xiangyi Chen, Pin-Yu Chen, Lee Martie, Lior Horesh, Mingyi Hong

Current deep neural networks are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification.

Quantization

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

1 code implementation ECCV 2020 Ren Wang, Gaoyuan Zhang, Sijia Liu, Pin-Yu Chen, JinJun Xiong, Meng Wang

When the training data are maliciously tampered, the predictions of the acquired deep neural network (DNN) can be manipulated by an adversary known as the Trojan attack (or poisoning backdoor attack).

Backdoor Attack

Proper Network Interpretability Helps Adversarial Robustness in Classification

1 code implementation ICML 2020 Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Cynthia Liu, Pin-Yu Chen, Shiyu Chang, Luca Daniel

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to adversarial attacks.

Adversarial Robustness Classification +2

A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning

no code implementations11 Jun 2020 Sijia Liu, Pin-Yu Chen, Bhavya Kailkhura, Gaoyuan Zhang, Alfred Hero, Pramod K. Varshney

Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning applications.

Reflecting After Learning for Understanding

no code implementations18 Oct 2019 Lee Martie, Mohammad Arif Ul Alam, Gaoyuan Zhang, Ryan R. Anderson

Using the framework on images from ImageNet, we demonstrate systems that unify 41% to 46% of predictions in general and unify 67% to 75% of predictions when the systems can explain their conceptual differences.

General Classification Image Classification

Adversarial T-shirt! Evading Person Detectors in A Physical World

1 code implementation ECCV 2020 Kaidi Xu, Gaoyuan Zhang, Sijia Liu, Quanfu Fan, Mengshu Sun, Hongge Chen, Pin-Yu Chen, Yanzhi Wang, Xue Lin

To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to-rigid objects such as T-shirts.

Visual Interpretability Alone Helps Adversarial Robustness

no code implementations25 Sep 2019 Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Pin-Yu Chen, Shiyu Chang, Luca Daniel

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability, and interpretability is itself susceptible to adversarial attacks.

Adversarial Robustness

Interpreting Adversarial Examples by Activation Promotion and Suppression

no code implementations3 Apr 2019 Kaidi Xu, Sijia Liu, Gaoyuan Zhang, Mengshu Sun, Pu Zhao, Quanfu Fan, Chuang Gan, Xue Lin

It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers.

Adversarial Robustness

Cannot find the paper you are looking for? You can Submit a new open access paper.