2023

AdvART: Adversarial Art for Camouflaged Object Detection Attacks

Guesmi, Amira, Bilasco, Ioan Marius, Shafique, Muhammad et al.

Understand

Physical adversarial attacks pose a significant practical threat as it deceives deep learning systems operating in the real world by producing prominent and maliciously designed physical perturbations.

Emphasizing the evaluation of naturalness is crucial in such attacks, as humans can readily detect and eliminate unnatural manipulations.
To overcome this limitation, recent work has proposed leveraging generative adversarial networks (GANs) to generate naturalistic patches, which may not catch human's attention.
However, these approaches suffer from a limited latent space which leads to an inevitable trade-off between naturalness and attack efficiency.

Built on

S. Thys et al. , “Fooling automated surveillance cameras: adversarial patches to attack person detection,” CoRR , vol. abs/1904.08653, 2019. [Online]. Available: http://arxiv.org/abs/1904.08653
Original
1904
Earlier work this paper cites.
M. Lee et al. , “On physical adversarial patches for object detection,” CoRR , vol. abs/1906.11897, 2019. [Online]. Available: http://arxiv.org/abs/1906.11897
Original
1906
Earlier work this paper cites.
Z. Wang and A. C. Bovik, “A universal image quality index,” IEEE signal processing letters , vol. 9, no. 3, pp. 81–84, 2002
Original
2002
Earlier work this paper cites.
Y. Zhao et al. , “Seeing isn’t believing: Towards more robust adversarial attack against real world object detectors,” ser. CCS ’19, New York, NY, USA, 2019, p. 1989–2004
2004
Earlier work this paper cites.
N. Dalal et al. , “Histograms of oriented gradients for human detection,” in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05) , vol. 1, 2005, pp. 886–893 vol. 1
2005
Earlier work this paper cites.
D. P. Kingma et al. , “Adam: A method for stochastic optimization,” 2014. [Online]. Available: https://arxiv.org/abs/1412.6980
Original
2014
Earlier work this paper cites.
M. Andriluka et al. , “2d human pose estimation: New benchmark and state of the art analysis,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , June 2014
2014
Earlier work this paper cites.
J. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” CoRR , vol. abs/1506.02640, 2015. [Online]. Available: http://arxiv.org/abs/1506.02640
Original
2015
Earlier work this paper cites.
A. Mahendran et al. , “Understanding deep image representations by inverting them,” in Proceedings of the IEEE conference on computer vision and pattern recognition , 2015, pp. 5188–5196
2015
Earlier work this paper cites.
A. Kurakin et al. , “Adversarial examples in the physical world,” CoRR , vol. abs/1607.02533, 2016. [Online]. Available: http://arxiv.org/abs/1607.02533
Original
2016
Earlier work this paper cites.

Similar

J. Redmon and A. Farhadi, “YOLO9000: better, faster, stronger,” CoRR , vol. abs/1612.08242, 2016. [Online]. Available: http://arxiv.org/abs/1612.08242
Original
2016
Cited alongside, same era.
I. Evtimov et al. , “Robust physical-world attacks on machine learning models,” CoRR , vol. abs/1707.08945, 2017. [Online]. Available: http://arxiv.org/abs/1707.08945
Original
2017
Cited alongside, same era.
A. Athalye et al. , “Synthesizing robust adversarial examples,” in International Conference on Machine Learning , 2017
2017
Cited alongside, same era.
K. Eykholt et al. , “Physical adversarial examples for object detectors,” in Proceedings of the 12th USENIX Conference on Offensive Technologies , ser. WOOT’18. USA: USENIX Association, 2018, p. 1
2018
Cited alongside, same era.
J. Redmon et al. , “Yolov3: An incremental improvement,” arXiv , 2018
2018
Cited alongside, same era.
L. Huang et al. , “UPC: learning universal physical camouflage attacks on object detectors,” CoRR , vol. abs/1909.04326, 2019
Original
2019
Cited alongside, same era.
J. Liu et al. , “A two-stage generative adversarial networks with semantic content constraints for adversarial example generation,” IEEE Access , vol. 8, pp. 205 766–205 777, 2020
2020
Cited alongside, same era.
A. Bochkovskiy et al. , “Yolov4: Yolov4: Optimal speed and accuracy of object detection,” arXiv , 2020
2020
Cited alongside, same era.
K. Xu, G. Zhang, S. Liu, Q. Fan, M. Sun, H. Chen et al. , “Adversarial t-shirt! evading person detectors in a physical world,” in ECCV , 2020
2020
Cited alongside, same era.
Z. Wu et al. , “Making an invisibility cloak: Real world adversarial attacks on object detectors,” in ECCV , 2020
2020
Cited alongside, same era.

Then

A. Voynov and A. Babenko, “Unsupervised discovery of interpretable directions in the gan latent space,” in International Conference on Machine Learning . PMLR, 2020, pp. 9786–9796
2020
Later among the works it cites.
T. Karras et al. , “Analyzing and improving the image quality of stylegan,” 2020
2020
Later among the works it cites.
Y.-C.-T. Hu et al. , “Naturalistic physical adversarial patch for object detectors,” in 2021 IEEE/CVF International Conference on Computer Vision (ICCV) , 2021, pp. 7828–7837
2021
Later among the works it cites.
S. Pavlitskaya et al. , “Feasibility of inconspicuous gan-generated adversarial patches against object detection,” 2022. [Online]. Available: https://arxiv.org/abs/2207.07347
Original
2022
Later among the works it cites.
T. Bai et al. , “Inconspicuous adversarial patches for fooling image-recognition systems on mobile devices,” IEEE Internet of Things Journal , vol. 9, no. 12, pp. 9515–9524, 2022
2022
Later among the works it cites.
A. Guesmi et al. , “Saam: Stealthy adversarial attack on monoculor depth estimation,” arXiv preprint arXiv:2308.03108 , 2023
Original
2023
Closest in time.
A. Guesmi, M. A. Hanif, I. Alouani, and M. Shafique, “Aparate: Adaptive adversarial patch for cnn-based monocular depth estimation for autonomous navigation,” arXiv preprint arXiv:2303.01351 , 2023
Original
2023
Closest in time.
A. Guesmi, M. A. Hanif, B. Ouni, and M. Shafique, “Physical adversarial attacks for camera-based smart systems: Current trends, categorization, applications, research challenges, and future outlook,” IEEE Access , 2023
2023
Closest in time.
A. Guesmi et al. , “Dap: A dynamic adversarial patch for evading person detectors,” 2023
2023
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…