English
Related papers

Related papers: Training for Trustworthy Saliency Maps: Adversaria…

200 papers

Saliency maps have been widely used to interpret the decisions of neural network classifiers and discover phenomena from their learned functions. However, standard gradient-based maps are frequently observed to be highly sensitive to the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Zhuorui Ye , Farzan Farnia

A Very recent trend has emerged to couple the notion of interpretability and adversarial robustness, unlike earlier efforts which solely focused on good interpretations or robustness against adversaries. Works have shown that adversarially…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Puneet Mangla , Vedant Singh , Vineeth N Balasubramanian

Gradient-based saliency maps have been widely used to explain the decisions of deep neural network classifiers. However, standard gradient-based interpretation maps, including the simple gradient and integrated gradient algorithms, often…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Shizhan Gong , Qi Dou , Farzan Farnia

Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to $\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothing. Under the…

Machine Learning · Computer Science 2022-12-21 Jongheon Jeong , Seojin Kim , Jinwoo Shin

In this work we introduce Salient Information Preserving Adversarial Training (SIP-AT), an intuitive method for relieving the robustness-accuracy trade-off incurred by traditional adversarial training. SIP-AT uses salient image regions to…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Timothy Redgrave , Adam Czajka

We present a novel method for reliably explaining the predictions of neural networks. We consider an explanation reliable if it identifies input features relevant to the model output by considering the input and the neighboring data points.…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Dohun Lim , Hyeonseok Lee , Sungchan Kim

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Aya Abdelsalam Ismail , Héctor Corrada Bravo , Soheil Feizi

Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image classifier.…

Machine Learning · Computer Science 2021-06-15 Yang Lu , Wenbo Guo , Xinyu Xing , William Stafford Noble

Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is vital for fostering trust and comprehension in these models.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Amira Guesmi , Nishant Suresh Aswani , Muhammad Shafique

Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is usually obtained via Adversarial Training, which explicitly…

Machine Learning · Computer Science 2024-10-01 Adrián Rodríguez-Muñoz , Tongzhou Wang , Antonio Torralba

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Ali Karkehabadi , Jamshid Hassanpour , Houman Homayoun , Avesta Sasan

Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Lin Li , Michael Spratling

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…

Machine Learning · Computer Science 2020-01-13 Hadi Salman , Greg Yang , Jerry Li , Pengchuan Zhang , Huan Zhang , Ilya Razenshteyn , Sebastien Bubeck

Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Ali Karkehabadi

Saliency maps that identify the most informative regions of an image for a classifier are valuable for model interpretability. A common approach to creating saliency maps involves generating input masks that mask out portions of an image to…

Computer Vision and Pattern Recognition · Computer Science 2020-10-21 Jason Phang , Jungkyu Park , Krzysztof J. Geras

Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensitive domains such as medical applications since…

Machine Learning · Computer Science 2019-10-21 Alexander Levine , Sahil Singla , Soheil Feizi

Recent studies on the adversarial vulnerability of neural networks have shown that models trained to be more robust to adversarial attacks exhibit more interpretable saliency maps than their non-robust counterparts. We aim to quantify this…

Machine Learning · Statistics 2019-05-13 Christian Etmann , Sebastian Lunz , Peter Maass , Carola-Bibiane Schönlieb

The different families of saliency methods, either based on contrastive signals, closed-form formulas mixing gradients with activations or on perturbation masks, all focus on which parts of an image are responsible for the model's…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Sylvestre-Alvise Rebuffi , Ruth Fong , Xu Ji , Hakan Bilen , Andrea Vedaldi

This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Felipe Torres Figueroa , Hanwei Zhang , Ronan Sicre , Yannis Avrithis , Stephane Ayache

Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…

Machine Learning · Computer Science 2025-02-10 Binghui Li , Yuanzhi Li
‹ Prev 1 2 3 10 Next ›