English
Related papers

Related papers: A Vulnerability of Attribution Methods Using Pre-S…

200 papers

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…

Machine Learning · Computer Science 2024-09-13 Oliver J. Sutton , Qinghua Zhou , Ivan Y. Tyukin , Alexander N. Gorban , Alexander Bastounis , Desmond J. Higham

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Levente Halmosi , Bálint Mohos , Márk Jelasity

Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…

Machine Learning · Computer Science 2020-10-20 Yiding Hao

In this paper, we present a novel attack against authorship attribution of source code. We exploit that recent attribution methods rest on machine learning and thus can be deceived by adversarial examples of source code. Our attack performs…

Machine Learning · Computer Science 2019-06-03 Erwin Quiring , Alwin Maier , Konrad Rieck

Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning…

Machine Learning · Computer Science 2020-01-30 Shahbaz Rezaei , Xin Liu

Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods. In light of these results, it remains unclear for practitioners how to use these…

Machine Learning · Computer Science 2024-01-09 Blair Bilodeau , Natasha Jaques , Pang Wei Koh , Been Kim

Despite the excelling performance of machine learning models, understanding their decisions remains a long-standing goal. Although commonly used attribution methods from explainable AI attempt to address this issue, they typically rely on…

Machine Learning · Computer Science 2025-11-20 Juan Miguel Lopez Alcaraz , Nils Strodthoff

Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring…

Machine Learning · Computer Science 2020-10-28 Ethan Weinberger , Joseph Janizek , Su-In Lee

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this…

Machine Learning · Statistics 2017-03-06 Volker Fischer , Mummadi Chaithanya Kumar , Jan Hendrik Metzen , Thomas Brox

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss…

Machine Learning · Computer Science 2023-03-23 Hao Wang , Chen Li , Jinzhe Jiang , Xin Zhang , Yaqian Zhao , Weifeng Gong

In this paper, we present an approach for evaluating attribution maps, which play a central role in interpreting the predictions of convolutional neural networks (CNNs). We show that the widely used insertion/deletion metrics are…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Lars Nieradzik , Henrike Stephani , Janis Keuper

Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that given a dataset and…

Cryptography and Security · Computer Science 2018-01-08 Jamie Hayes , George Danezis

The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model. Attribution maps are generally used to highlight the…

Machine Learning · Computer Science 2023-08-02 Ian E. Nielsen , Ravi P. Ramachandran , Nidhal Bouaynaya , Hassan M. Fathallah-Shaykh , Ghulam Rasool

There has been a recent push in making machine learning models more interpretable so that their performance can be trusted. Although successful, these methods have mostly focused on the deep learning methods while the fundamental…

Machine Learning · Computer Science 2022-06-16 David Steinmann , Matej Zečević , Devendra Singh Dhami , Kristian Kersting

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating…

Machine Learning · Computer Science 2024-07-18 Avery Ma , Amir-massoud Farahmand , Yangchen Pan , Philip Torr , Jindong Gu

Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…

Cryptography and Security · Computer Science 2024-08-28 Dipkamal Bhusal , Md Tanvirul Alam , Monish K. Veerabhadran , Michael Clifford , Sara Rampazzi , Nidhi Rastogi

As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…

Machine Learning · Computer Science 2021-03-19 Gabriel D. Cantareira , Rodrigo F. Mello , Fernando V. Paulovich

Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on Deep Q-Networks (DQNs)…

Machine Learning · Computer Science 2017-01-17 Vahid Behzadan , Arslan Munir

We present a method for neural network interpretability by combining feature attribution with counterfactual explanations to generate attribution maps that highlight the most discriminative features between pairs of classes. We show that…

Machine Learning · Computer Science 2021-09-29 Nils Eckstein , Alexander S. Bates , Gregory S. X. E. Jefferis , Jan Funke

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

Computation and Language · Computer Science 2026-04-21 Jonathan Kamp , Roos Bakker , Dominique Blok