[HTML][HTML] A comprehensive survey of robust deep learning in computer vision
Deep learning has presented remarkable progress in various tasks. Despite the excellent
performance, deep learning models remain not robust, especially to well-designed …
performance, deep learning models remain not robust, especially to well-designed …
Interpretable and trustworthy deepfake detection via dynamic prototypes
In this paper we propose a novel human-centered approach for detecting forgery in face
images, using dynamic prototypes as a form of visual explanations. Currently, most state-of …
images, using dynamic prototypes as a form of visual explanations. Currently, most state-of …
Towards security threats of deep learning systems: A survey
Deep learning has gained tremendous success and great popularity in the past few years.
However, deep learning systems are suffering several inherent weaknesses, which can …
However, deep learning systems are suffering several inherent weaknesses, which can …
Fastened crown: Tightened neural network robustness certificates
The rapid growth of deep learning applications in real life is accompanied by severe safety
concerns. To mitigate this uneasy phenomenon, much research has been done providing …
concerns. To mitigate this uneasy phenomenon, much research has been done providing …
Improving neural network verification through spurious region guided refinement
We propose a spurious region guided refinement approach for robustness verification of
deep neural networks. Our method starts with applying the DeepPoly abstract domain to …
deep neural networks. Our method starts with applying the DeepPoly abstract domain to …
Securing DNN for smart vehicles: An overview of adversarial attacks, defenses, and frameworks
S Almutairi, A Barnawi - Journal of Engineering and Applied Science, 2023 - Springer
Recently, many applications have begun to employ deep neural networks (DNN), such as
image recognition and safety-critical applications, for more accurate results. One of the most …
image recognition and safety-critical applications, for more accurate results. One of the most …
Revisiting gradient regularization: Inject robust saliency-aware weight bias for adversarial defense
Despite regularizing the Jacobians of neural networks to enhance model robustness has
directly theoretical correlation with model prediction stability, a large defense performance …
directly theoretical correlation with model prediction stability, a large defense performance …
Probabilistic verification and reachability analysis of neural networks via semidefinite programming
Quantifying the robustness of neural networks or verifying their safety properties against
input uncertainties or adversarial attacks have become an important research area in …
input uncertainties or adversarial attacks have become an important research area in …
[图书][B] Adversarial robustness for machine learning
Adversarial Robustness for Machine Learning summarizes the recent progress on this topic
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …
CC-Cert: A probabilistic approach to certify general robustness of neural networks
M Pautov, N Tursynbek, M Munkhoeva… - Proceedings of the …, 2022 - ojs.aaai.org
In safety-critical machine learning applications, it is crucial to defend models against
adversarial attacks---small modifications of the input that change the predictions. Besides …
adversarial attacks---small modifications of the input that change the predictions. Besides …