2023

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation

Guesmi, Amira, Hanif, Muhammad Abdullah, Ouni, Bassem et al.

Understand

In this paper, we investigate the vulnerability of MDE to adversarial patches.

We propose a novel \underline{S}tealthy \underline{A}dversarial \underline{A}ttacks on \underline{M}DE (SAAM) that compromises MDE by either corrupting the estimated distance or causing an object to seamlessly blend into its surroundings.
Our experiments, demonstrate that the designed stealthy patch successfully causes a DNN-based MDE to misestimate the depth of objects.
In fact, our proposed adversarial patch achieves a significant 60\% depth error with 99\% ratio of the affected region.

Built on

Imagenet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei · 2009
Earlier work this paper cites.
Indoor segmentation and support inference from rgbd images
Pushmeet Kohli Nathan Silberman, Derek Hoiem and Rob Fergus · 2012
Earlier work this paper cites.
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian J. Goodfellow, and Rob Fergus · 2014
Earlier work this paper cites.
Explaining and harnessing adversarial examples, 2014
Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization, 2014
Diederik P. Kingma and Jimmy Ba · 2014
Earlier work this paper cites.
Understanding deep image representations by inverting them
Aravindh Mahendran and Andrea Vedaldi · 2015
Earlier work this paper cites.
Towards evaluating the robustness of neural networks
Original
N. Carlini and D. A. Wagner · 2016
Earlier work this paper cites.
Simple black-box adversarial perturbations for deep networks
Original
N. Narodytska and S. P. Kasiviswanathan · 2016
Earlier work this paper cites.
Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition
Mahmood Sharif, Sruti Bhagavatula, Lujo Bauer, and Michael K. Reiter · 2016
Earlier work this paper cites.
Deep residual learning for image recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Earlier work this paper cites.
A study of the effect of JPG compression on adversarial images
Original
Gintare Karolina Dziugaite, Zoubin Ghahramani, and Daniel M. Roy · 2016
Earlier work this paper cites.
Feature squeezing: Detecting adversarial examples in deep neural networks
Original
Weilin Xu, David Evans, and Yanjun Qi · 2016
Earlier work this paper cites.
Cnn-slam: Real-time dense monocular slam with learned depth prediction
Keisuke Tateno, Federico Tombari, Iro Laina, and Nassir Navab · 2017
Earlier work this paper cites.
Decision-based adversarial attacks: Reliable attacks against black-box machine learning models, 2017
W. Brendel, J. Rauber, and M. Bethge · 2017
Earlier work this paper cites.

Similar

Universal adversarial perturbations, 2017
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, and Pascal Frossard · 2017
Cited alongside, same era.
Digging into self-supervised monocular depth estimation
Original
Clément Godard, Oisin Mac Aodha, and Gabriel J. Brostow · 2018
Cited alongside, same era.
Taskonomy: Disentangling task transfer learning
Amir R. Zamir, Alexander Sax, William Shen, Leonidas J. Guibas, Jitendra Malik, and Silvio Savarese · 2018
Cited alongside, same era.
Boosting adversarial attacks with momentum
Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, and Jianguo Li · 2018
Cited alongside, same era.
Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving
Yan Wang, Wei-Lun Chao, Divyansh Garg, Bharath Hariharan, Mark Campbell, and Kilian Q. Weinberger · 2019
Cited alongside, same era.
Digging into self-supervised monocular depth estimation, 2019
Clément Godard, Oisin Mac Aodha, Michael Firman, and Gabriel Brostow · 2019
Cited alongside, same era.
Boundary attack++: Query-efficient decision-based adversarial attack
Original
J. Chen and M. I. Jordan · 2019
Cited alongside, same era.
Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer
Original
Katrin Lasinger, René Ranftl, Konrad Schindler, and Vladlen Koltun · 2019
Cited alongside, same era.
Web stereo video supervision for depth prediction from dynamic scenes
Original
Chaoyang Wang, Simon Lucey, Federico Perazzi, and Oliver Wang · 2019
Cited alongside, same era.
Pytorch: An imperative style, high-performance deep learning library
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala · 2019
Cited alongside, same era.
Defending against whitebox adversarial attacks via randomized discretization
Yuchen Zhang and Percy Liang · 2019
Cited alongside, same era.
Lm-reloc: Levenberg-marquardt based direct visual relocalization
Original
Lukas von Stumberg, Patrick Wenzel, Nan Yang, and Daniel Cremers · 2020
Cited alongside, same era.

Then

Fast depth prediction and obstacle avoidance on a monocular drone using probabilistic convolutional neural network
Xin Yang, Jingyu Chen, Yuanjie Dang, Hongcheng Luo, Yuesheng Tang, Chunyuan Liao, Peng Chen, and Kwang-Ting Cheng · 2021
Later among the works it cites.
Monorec: Semi-supervised dense reconstruction in dynamic environments from a single moving camera
Felix Wimbauer, Nan Yang, Lukas von Stumberg, Niclas Zeller, and Daniel Cremers · 2021
Later among the works it cites.
Learning to recover 3d scene shape from a single image
Wei Yin, Jianming Zhang, Oliver Wang, Simon Niklaus, Long Mai, Simon Chen, and Chunhua Shen · 2021
Later among the works it cites.
Physical attack on monocular depth estimation with optimal adversarial patches, 2022
Zhiyuan Cheng, James Liang, Hongjun Choi, Guanhong Tao, Zhiwen Cao, Dongfang Liu, and Xiangyu Zhang · 2022
Later among the works it cites.
Room: Adversarial machine learning attacks under real-time constraints
Amira Guesmi, Khaled N. Khasawneh, Nael Abu-Ghazaleh, and Ihsen Alouani · 2022
Later among the works it cites.
Global-local path networks for monocular depth estimation with vertical cutdepth, 2022
Doyeon Kim, Woonghyun Ka, Pyungwhan Ahn, Donggyu Joo, Sehwan Chun, and Junmo Kim · 2022
Later among the works it cites.
Dap: A dynamic adversarial patch for evading person detectors, 2023
Amira Guesmi, Ruitian Ding, Muhammad Abdullah Hanif, Ihsen Alouani, and Muhammad Shafique · 2023
Closest in time.
Aparate: Adaptive adversarial patch for cnn-based monocular depth estimation for autonomous navigation, 2023
Amira Guesmi, Muhammad Abdullah Hanif, Ihsen Alouani, and Muhammad Shafique · 2023
Closest in time.
Advart: Adversarial art for camouflaged object detection attacks, 2023
Amira Guesmi, Ioan Marius Bilasco, Muhammad Shafique, and Ihsen Alouani · 2023
Closest in time.
The art of defense: Letting networks fool the attacker
Jinlai Zhang, Yinpeng Dong, Minchi Kuang, Binbin Liu, Bo Ouyang, Jihong Zhu, Houqing Wang, and Yanmei Meng · 2023
Closest in time.
Oddr: Outlier detection & dimension reduction based defense against adversarial patches
Original
Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, and Muhammad Shafique · 2023
Closest in time.
Defensivedr: Defending against adversarial patches using dimensionality reduction
Original
Nandish Chattopadhyay, Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, and Muhammad Shafique · 2023
Closest in time.
Image masking for robust self-supervised monocular depth estimation, 2023
Hemang Chawla, Kishaan Jeeveswaran, Elahe Arani, and Bahram Zonooz · 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…