English
Related papers

Related papers: Interpretable BoW Networks for Adversarial Example…

200 papers

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to…

Computation and Language · Computer Science 2018-09-26 Moustafa Alzantot , Yash Sharma , Ahmed Elgohary , Bo-Jhang Ho , Mani Srivastava , Kai-Wei Chang

Sentiment analysis is known as one of the most crucial tasks in the field of natural language processing and Convolutional Neural Network (CNN) is one of those prominent models that is commonly used for this aim. Although convolutional…

Computation and Language · Computer Science 2021-02-24 Hossein Sadr , Mozhdeh Nazari Solimandarabi , Mir Mohsen Pedram , Mohammad Teshnehlab

Discovering causal models from observational and interventional data is an important first step preceding what-if analysis or counterfactual reasoning. As has been shown before, the direction of pairwise causal relations can, under certain…

Machine Learning · Computer Science 2017-01-04 Karamjit Singh , Garima Gupta , Lovekesh Vig , Gautam Shroff , Puneet Agarwal

State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable against adversarial attacks, i.e., non-perceptible…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Kira Maag , Asja Fischer

Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input. However, these models are vulnerable to adversarial perturbations--small input changes crafted explicitly to…

Machine Learning · Statistics 2017-11-17 Reuben Feinman , Ryan R. Curtin , Saurabh Shintre , Andrew B. Gardner

Deep computer vision systems being vulnerable to imperceptible and carefully crafted noise have raised questions regarding the robustness of their decisions. We take a step back and approach this problem from an orthogonal direction. We…

Computer Vision and Pattern Recognition · Computer Science 2019-04-18 Sadaf Gulshad , Jan Hendrik Metzen , Arnold Smeulders , Zeynep Akata

Deep Neural Networks (DNNs) are known to be vulnerable to the maliciously generated adversarial examples. To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of…

Computer Vision and Pattern Recognition · Computer Science 2019-11-18 Xiaofeng Mao , Yuefeng Chen , Yuhong Li , Yuan He , Hui Xue

Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Yinpeng Dong , Tianyu Pang , Hang Su , Jun Zhu

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks: carefully constructed perturbations to an image can seriously impair classification accuracy, while being imperceptible to humans. While there has been a significant amount…

Machine Learning · Computer Science 2020-12-23 Can Bakiskan , Metehan Cekic , Ahmet Dundar Sezer , Upamanyu Madhow

Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems. However, these deep models are perceived as "black box" methods considering the lack of understanding of their…

Computer Vision and Pattern Recognition · Computer Science 2018-11-13 Aditya Chattopadhyay , Anirban Sarkar , Prantik Howlader , Vineeth N Balasubramanian

Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Ali Borji

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Hossein Hosseini , Radha Poovendran

Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing…

Computer Vision and Pattern Recognition · Computer Science 2019-06-04 Cihang Xie , Zhishuai Zhang , Yuyin Zhou , Song Bai , Jianyu Wang , Zhou Ren , Alan Yuille

We investigate the problem of identifying adversarial attacks on image-based neural networks. We present intriguing experimental results showing significant discrepancies between the explanations generated for the predictions of a model on…

Machine Learning · Computer Science 2020-03-13 Sean Saito , Jin Wang

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

Machine Learning · Computer Science 2023-09-12 Stephen Casper , Max Nadeau , Dylan Hadfield-Menell , Gabriel Kreiman

The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach…

Machine Learning · Computer Science 2019-04-16 Octavian Suciu , Scott E. Coull , Jeffrey Johns

Semantic segmentation constitutes an integral part of medical image analyses for which breakthroughs in the field of deep learning were of high relevance. The large number of trainable parameters of deep neural networks however renders them…

Computer Vision and Pattern Recognition · Computer Science 2017-02-28 Simon Kohl , David Bonekamp , Heinz-Peter Schlemmer , Kaneschka Yaqubi , Markus Hohenfellner , Boris Hadaschik , Jan-Philipp Radtke , Klaus Maier-Hein

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Graph neural network (GNN) explanations have largely been facilitated through post-hoc introspection. While this has been deemed successful, many post-hoc explanation methods have been shown to fail in capturing a model's learned…

Machine Learning · Computer Science 2021-06-28 Donald Loveland , Shusen Liu , Bhavya Kailkhura , Anna Hiszpanski , Yong Han