Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

By Naveed Akhtar, Ajmal Saeed Mian. 2018

2,074 citations recorded by the source corpus.

Deep learning is at the heart of the current rise of artificial intelligence. In the field of computer vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas, deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently led to a large influx of contributions in this direction. This paper presents the first comprehensive survey on adversarial attacks on deep learning in computer vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Hardware and Architecture, Safety, Robustness & Interpretability, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Hardware and Architecture

In Safety, Robustness & Interpretability

In Signal Processing

Citations in the corpus

Online Adversarial Attacks (2021, background): “Critical to the study of adversarial attacks is specifying the threat model Akhtar and Mian [2018], which outlines the adversarial capabilities of an attacker and the level of information available in crafting attacks. Canonical examples include the whitebox threat model Madry et al. [2017], where t”
Adversarial Example Games (2020, background): “Adversarial attacks can be classiﬁed under different threat models, which impose different access and resource restrictions on the attacker [1].”
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack (2018, background): “In addition to image classification, attacks to other DNN-powered tasks have also been actively investigated, such as visual question answering [43, 1], image captioning [10], semantic segmentation [31, 1] and etc [12, 8, 39].”
Training verified learners with learned verifiers (2018, background): “Starting with the work of Szegedy et al. [26], there have been several papers both on understanding adversarial attacks on neural networks and developing defense strategies against these attacks [1, 21, 24, 30–32].”
CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models (2019, methodology): “Other general methods on explainability, fairness and robustness have been described by [Guidotti et al., 2018b],[Binns, 2017], and [Akhtar and Mian, 2018] respectively.”
Recent Progress on Generative Adversarial Networks (GANs): A Survey (2019, background): “At present, the vulnerability of deep learning to subtle adversarial perturbations is a common phenomenon [79].”
Adversarial Geometry and Lighting using a Differentiable Renderer (2018, background): “Since then, adversarial attacking has been a rich research area [1, 41, 10, 35, 21, 27, 6, 30, 28, 4].”
Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning (2020, background): “There is a rapidly growing literature on test-time attacks on neural-network image classifiers [3, 37, 38, 49, 69]; some employ only black-box model queries [15, 33] rather than gradient-based optimization.”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “To be against adversarial attacks [118], [119], references [120], [121] utilize GANs to conduct the right defense.”
Code Prediction by Feeding Trees to Transformers (2020, background): “Despite their wide adoption in many areas of computing, deep learning models have been repeatedly shown susceptible to adversarial examples [33]–[35].”
Adversarial Attacks on Face Detectors Using Neural Net Based Constrained Optimization (2018, background): “We direct the interested reader to this survey for a detailed description [18] of the different attack strategies and defenses.”
Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey (2019, background): “The work in [2] provides a comprehensive review on the adversarial attacks on deep learning models used in computer vision tasks.”