Double Targeted Universal Adversarial Perturbations

30/11/2020

Double Targeted Universal Adversarial Perturbations

Philipp Benz, Chaoning Zhang, Tooba Imtiaz, In So Kweon

Keywords:

Abstract Paper Similar Papers

Abstract: Despite their impressive performance, deep neural networks (DNNs) are widely known to be vulnerable to adversarial attacks, which makes it challenging for them to be deployed in security-sensitive applications, such as autonomous driving. Image-dependent perturbations can fool a network for one specific image, while universal adversarial perturbations are capable of fooling a network for samples from all classes without selection. We introduce a double targeted universal adversarial perturbations (DT-UAPs) to bridge the gap between the instance-discriminative image-dependent perturbations and the generic universal perturbations. This universal perturbation attacks one targeted source class to sink class, while having a limited adversarial effect on other non-targeted source classes, for avoiding raising suspicions. Targeting the source and sink class simultaneously, we term it double targeted attack (DTA). This provides an attacker with the freedom to perform precise attacks on a DNN model while raising little suspicion. We show the effectiveness of the proposed DTA algorithm on a wide range of datasets and also demonstrate its potential as a physical attack.

The video of this talk cannot be embedded. You can watch it here:

https://accv2020.github.io/miniconf/poster_759.html

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

18/11/2020

Towards understanding and improving the transferability of adversarial examples in deep neural networks

Lei Wu, Zhanxing Zhu

Keywords Paper

0

0

0

0

10:28

14/06/2020

Enhancing Cross-Task Black-Box Transferability of Adversarial Examples With Dispersion Reduction

Yantao Lu, Yunhan Jia, Jianyu Wang and
Bai Li, Weiheng Chai, Lawrence Carin, Senem Velipasalar

Keywords Paper

adversarial example, black-box attack, cross tasks, transferability, deep neural network

0

0

0

0

1:01

12/07/2020

Adversarial Neural Pruning with Latent Vulnerability Suppression

Divyam Madaan, Jinwoo Shin, Sung Ju Hwang

Keywords Paper

Adversarial Examples

0

0

0

0

14:43

02/02/2021

Proactive Privacy-preserving Learning for Retrieval

Peng-Fei Zhang, Zi Huang, Xin-Shun Xu

Keywords Paper

0

0

0

0

17:14

06/12/2021

Disrupting Deep Uncertainty Estimation Without Harming Accuracy

Ido Galil, Ran El-Yaniv

Keywords Paper

deep learning, machine learning, adversarial robustness and security

0

0

0

0

9:14

14/06/2020

Boosting the Transferability of Adversarial Samples via Attention

Weibin Wu, Yuxin Su, Xixian Chen and
Shenglin Zhao, Irwin King, Michael R. Lyu, Yu-Wing Tai

Keywords Paper

adversarial learning, adversarial attack methods

0

0

0

0

1:01

06/12/2021

Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks

Yonggan Fu, Qixuan Yu, Yang Zhang and
Shang Wu, Xu Ouyang, David Cox, Yingyan Lin

Keywords Paper

deep learning, robustness, adversarial robustness and security

0

0

0

0

12:48

06/12/2021

Backdoor Attack with Imperceptible Input and Latent Modification

Khoa D Doan, Yingjie Lao, Ping Li

Keywords Paper

deep learning, optimization, adversarial robustness and security, generative model

0

0

0

0

12:27

02/02/2021

Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

Jinyu Tian, Jiantao Zhou, Yuanman Li, Jia Duan

Keywords Paper

0

0

0

0

18:59

26/04/2020

Improving Adversarial Robustness Requires Revisiting Misclassified Examples

Yisen Wang, Difan Zou, Jinfeng Yi and
James Bailey, Xingjun Ma, Quanquan Gu

Keywords Paper

Robustness, Adversarial Defense, Adversarial Training

0

0

0

0

5:02

06/12/2021

Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data

Dongmin Park, Hwanjun Song, Minseok Kim, Jae-Gil Lee

Keywords Paper

deep learning, machine learning

0

0

0

0

14:30

14/06/2020

Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder

Guanlin Li, Shuya Ding, Jun Luo, Chang Liu

Keywords Paper

adversarial defense, feature denoise, multi-task learning, self-supervised learning, image restoration, lipschitz constant constraint, feature pyramid decoder

0

0

0

0

1:01

14/06/2020

PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving

Zelun Kong, Junfeng Guo, Ang Li, Cong Liu

Keywords Paper

adversarail ml, computer vision, autonomous driving, gan, physical-world adversarail example

0

0

0

0

1:00

19/08/2021

Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity

Yajie Wang, Shangbo Wu, Wenyi Jiang and
Shengang Hao, Yu-an Tan, Quanxin Zhang

Keywords Paper

Machine Learning, Adversarial Machine Learning, Deep Learning

0

0

0

0

12:35

18/07/2021

Towards Defending against Adversarial Examples via Attack-Invariant Features

Dawei Zhou, Tongliang Liu, Bo Han and
Nannan Wang, Chunlei Peng, Xinbo Gao

Keywords Paper

Algorithms, Adversarial Examples

0

0

0

0

5:19

14/06/2020

Conditional Gaussian Distribution Learning for Open Set Recognition

Xin Sun, Zhenning Yang, Chi Zhang and
Keck-Voon Ling, Guohao Peng

Keywords Paper

open set recognition, conditional variational auto-encoder, gaussian distribution learning, probabilistic ladder architecture.

0

0

0

0

1:01

14/06/2020

QEBA: Query-Efficient Boundary-Based Blackbox Attack

Huichen Li, Xiaojun Xu, Xiaolu Zhang and
Shuang Yang, Bo Li

Keywords Paper

adversarial machine learning, black-box attack, boundary-based attack, attacking public api

0

0

0

0

1:01

14/06/2020

Defending Against Model Stealing Attacks With Adaptive Misinformation

Sanjay Kariyappa, Moinuddin K. Qureshi

Keywords Paper

model stealing, security, machine learning, deep learning

0

0

0

0

1:01

23/08/2020

Interpretability is a kind of safety: An interpreter-based ensemble for adversary defense

Jingyuan Wang, Yufan Wu, Mingxuan Li and
Xin Lin, Junjie Wu, Chao Li

Keywords Paper

DNN interpretation, adversarial example defense, ensemble

0

0

0

0

10:04

06/12/2021

Adversarial Feature Desensitization

Pouya Bashivan, Reza Bayat, Adam Ibrahim and
Kartik Ahuja, Mojtaba Faramarzi, Touraj Laleh, Blake Richards, Irina Rish

Keywords Paper

deep learning, robustness, adversarial robustness and security, domain adaptation

0

0

0

0

13:27

14/06/2020

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

Yuheng Zhang, Ruoxi Jia, Hengzhi Pei and
Wenxiao Wang, Bo Li, Dawn Song

Keywords Paper

model inversion attack, deep neural network, generative adversarial network, differential privacy

0

0

0

0

5:01

14/06/2020

A Self-supervised Approach for Adversarial Robustness

Muzammal Naseer, Salman Khan, Munawar Hayat and
Fahad Shahbaz Khan, Fatih Porikli

Keywords Paper

self-supervision, defense, attack, perceptual-features, classification, segmentation, object-detection, adversarial-learning, dynamic-defense, zero-shot

0

0

0

0

5:01

14/06/2020

Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles

Ranjie Duan, Xingjun Ma, Yisen Wang and
James Bailey, A. K. Qin, Yun Yang

Keywords Paper

adversarial example, physical attack, camouflage

0

0

0

0

1:01

26/04/2020

Unrestricted Adversarial Examples via Semantic Manipulation

Anand Bhattad, Min Jin Chong, Kaizhao Liang and
Bo Li, D. A. Forsyth

Keywords Paper

Adversarial Examples, Semantic Manipulation, Image Colorization, Texture Transfer

0

0

0

0

3:51

18/07/2021

Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference

Yonggan Fu, Qixuan Yu, Meng Li and
Vikas Chandra, Yingyan Lin

Keywords Paper

Algorithms, Adversarial Examples

0

0

0

0

5:20

06/12/2020

Input-Aware Dynamic Backdoor Attack

Tuan Anh Nguyen, Anh Tran

Keywords Paper

0

0

0

0

3:21

14/06/2020

Equalization Loss for Long-Tailed Object Recognition

Jingru Tan, Changbao Wang, Buyu Li and
Quanquan Li, Wanli Ouyang, Changqing Yin, Junjie Yan

Keywords Paper

long tail, object detection, lvis, object recognition

0

0

0

0

1:00

18/07/2021

Neural Tangent Generalization Attacks

Jimmy Yuan, Shan-Hung (Brandon) Wu

Keywords Paper

Algorithms, Adversarial Examples

0

0

0

0

5:14

06/12/2020

Adversarial Learning for Robust Deep Clustering

Xu Yang, Cheng Deng, Kun Wei and
Junchi Yan, Wei Liu

Keywords Paper

0

0

0

0

3:23

12/07/2020

Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup

Jang-Hyun Kim, Wonho Choo, Hyun Oh Song

Keywords Paper

Deep Learning - Algorithms

0

0

0

0

13:40

02/02/2021

A Unified Multi-Scenario Attacking Network for Visual Object Tracking

Xuesong Chen, Canmiao Fu, Feng Zheng and
Yong Zhao, Hongsheng Li, Ping Luo, Guo-Jun Qi

Keywords Paper

0

0

0

0

18:19

12/07/2020

On Breaking Deep Generative Model-based Defenses and Beyond

Yanzhi Chen, Renjie Xie, Zhanxing Zhu

Keywords Paper

Adversarial Examples

0

0

0

0

10:33

26/04/2020

EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness Against Adversarial Attacks

Sanchari Sen, Balaraman Ravindran, Anand Raghunathan

Keywords Paper

ensembles, mixed precision, robustness, adversarial attacks

0

0

0

0

4:25

03/05/2021

Protecting DNNs from Theft using an Ensemble of Diverse Models

Sanjay Kariyappa, Atul Prakash, Moinuddin K Qureshi

Keywords Paper

machine learning security, Model stealing

0

0

0

0

5:05

03/05/2021

Towards Robust Neural Networks via Close-loop Control

Zhuotong Chen, Qianxiao Li, Zheng Zhang

Keywords Paper

dynamical system, neural network robustness, optimal control

0

0

0

0

4:47

26/08/2020

Adversarial Risk Bounds through Sparsity based Compression

Emilio Balda, Niklas Koep, Arash Behboodi, Rudolf Mathar

Keywords Paper

0

0

0

0

15:15

14/06/2020

Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes

Sravanti Addepalli, Vivek B.S., Arya Baburaj and
Gaurang Sriramanan, R. Venkatesh Babu

Keywords Paper

adversarial robustness, adversarial defense, adversarial training, fast adversarial training, adversary-free training, adversarial attacks, efficient adversarial training, generalization, feature consistency, deep neural networks

0

0

0

0

1:01

18/07/2021

Enhancing Robustness of Neural Networks through Fourier Stabilization

Netanel Raviv, Aidan Kelley, Minzhe Guo, Yevgeniy Vorobeychik

Keywords Paper

Probabilistic Methods, Variational Inference, Algorithms, Boosting and Ensemble Methods; Probabilistic Methods; Probabilistic Methods, Bayesian Theory, Social Aspects of Machine Learning, Privacy, Anonymity, and Security

0

0

0

0

4:57

18/07/2021

Learning Deep Neural Networks under Agnostic Corrupted Supervision

Boyang Liu, Mengying Sun, Ding Wang and
Pang-Ning Tan, Jiayu Zhou

Keywords Paper

Algorithms, Supervised Learning

0

0

0

0

4:59

06/12/2021

Excess Capacity and Backdoor Poisoning

Naren Manoj, Avrim Blum

Keywords Paper

theory, machine learning, robustness, adversarial robustness and security

0

0

0

0

10:38