Timezone: »

Blackbox Attacks via Surrogate Ensemble Search
Zikui Cai · Chengyu Song · Srikanth Krishnamurthy · Amit Roy-Chowdhury · Salman Asif

Wed Dec 07 05:00 PM -- 07:00 PM (PST) @
Blackbox adversarial attacks can be categorized into transfer- and query-based attacks. Transfer methods do not require any feedback from the victim model, but provide lower success rates compared to query-based methods. Query attacks often require a large number of queries for success. To achieve the best of both approaches, recent efforts have tried to combine them, but still require hundreds of queries to achieve high success rates (especially for targeted attacks). In this paper, we propose a novel method for Blackbox Attacks via Surrogate Ensemble Search (BASES) that can generate highly successful blackbox attacks using an extremely small number of queries. We first define a perturbation machine that generates a perturbed image by minimizing a weighted loss function over a fixed set of surrogate models. To generate an attack for a given victim model, we search over the weights in the loss function using queries generated by the perturbation machine. Since the dimension of the search space is small (same as the number of surrogate models), the search requires a small number of queries. We demonstrate that our proposed method achieves better success rate with at least $30\times$ fewer queries compared to state-of-the-art methods on different image classifiers trained with ImageNet (including VGG-19, DenseNet-121, and ResNext-50). In particular, our method requires as few as 3 queries per image (on average) to achieve more than a $90\%$ success rate for targeted attacks and 1--2 queries per image for over a $99\%$ success rate for untargeted attacks. Our method is also effective on Google Cloud Vision API and achieved a $91\%$ untargeted attack success rate with 2.9 queries per image. We also show that the perturbations generated by our proposed method are highly transferable and can be adopted for hard-label blackbox attacks. Furthermore, we argue that BASES can be used to create attacks for a variety of tasks and show its effectiveness for attacks on object detection models. Our code is available at https://github.com/CSIPlab/BASES.

Author Information

Zikui Cai (University of California, Riverside)
Chengyu Song (University of California, Riverside)
Srikanth Krishnamurthy (, University of California, Riverside)
Amit Roy-Chowdhury (University of California, Riverside)

Amit Roy-Chowdhury received his PhD from the University of Maryland, College Park (UMCP) in 2002 and joined the University of California, Riverside (UCR) in 2004 where he is a Professor and Bourns Family Faculty Fellow of Electrical and Computer Engineering, Director of the Center for Robotics and Intelligent Systems, and Cooperating Faculty in the department of Computer Science and Engineering. He leads the Video Computing Group at UCR, working on foundational principles of computer vision, image processing, and statistical learning, with applications in cyber-physical, autonomous and intelligent systems. He has published over 200 papers in peer-reviewed journals and conferences. He is the first author of the book Camera Networks: The Acquisition and Analysis of Videos Over Wide Areas. He is on the editorial boards of major journals and program committees of the main conferences in his area. His students have been first authors on multiple papers that received Best Paper Awards at major international conferences, including ICASSP and ICMR. He is a Fellow of the IEEE and IAPR, received the Doctoral Dissertation Advising/Mentoring Award 2019 from UCR, and the ECE Distinguished Alumni Award from UMCP.

Salman Asif (University of California, Riverside)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors

  • 2022 Poster: AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments »
    Sudipta Paul · Amit Roy-Chowdhury · Anoop Cherian
  • 2022 Poster: GAMA: Generative Adversarial Multi-Object Scene Attacks »
    Abhishek Aich · Calvin-Khang Ta · Akash Gupta · Chengyu Song · Srikanth Krishnamurthy · Salman Asif · Amit Roy-Chowdhury
  • 2021 Poster: Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition »
    Jiaming Liu · Salman Asif · Brendt Wohlberg · Ulugbek Kamilov
  • 2021 Poster: Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations »
    Shasha Li · Abhishek Aich · Shitong Zhu · Salman Asif · Chengyu Song · Amit Roy-Chowdhury · Srikanth Krishnamurthy
  • 2019 : Poster Session »
    Jonathan Scarlett · Piotr Indyk · Ali Vakilian · Adrian Weller · Partha P Mitra · Benjamin Aubin · Bruno Loureiro · Florent Krzakala · Lenka Zdeborová · Kristina Monakhova · Joshua Yurtsever · Laura Waller · Hendrik Sommerhoff · Michael Moeller · Rushil Anirudh · Shuang Qiu · Xiaohan Wei · Zhuoran Yang · Jayaraman Thiagarajan · Salman Asif · Michael Gillhofer · Johannes Brandstetter · Sepp Hochreiter · Felix Petersen · Dhruv Patel · Assad Oberai · Akshay Kamath · Sushrut Karmalkar · Eric Price · Ali Ahmed · Zahra Kadkhodaie · Sreyas Mohan · Eero Simoncelli · Carlos Fernandez-Granda · Oscar Leong · Wesam Sakla · Rebecca Willett · Stephan Hoyer · Jascha Sohl-Dickstein · Sam Greydanus · Gauri Jagatap · Chinmay Hegde · Michael Kellman · Jonathan Tamir · Nouamane Laanait · Ousmane Dia · Mirco Ravanelli · Jonathan Binas · Negar Rostamzadeh · Shirin Jalali · Tiantian Fang · Alex Schwing · SĂ©bastien Lachapelle · Philippe Brouillard · Tristan Deleu · Simon Lacoste-Julien · Stella Yu · Arya Mazumdar · Ankit Singh Rawat · Yue Zhao · Jianshu Chen · Xiaoyang Li · Hubert Ramsauer · Gabrio Rizzuti · Nikolaos Mitsakos · Dingzhou Cao · Thomas Strohmer · Yang Li · Pei Peng · Gregory Ongie