English
Related papers

Related papers: Assessing Systematic Weaknesses of DNNs using Coun…

200 papers

The complexity of modern electro-mechanical systems require the development of sophisticated diagnostic methods like anomaly detection capable of detecting deviations. Conventional anomaly detection approaches like signal processing and…

Machine Learning · Computer Science 2025-01-07 Abhishek Srinivasan , Varun Singapuri Ravi , Juan Carlos Andresen , Anders Holst

Currently, there is a significant amount of research being conducted in the field of artificial intelligence to improve the explainability and interpretability of deep learning models. It is found that if end-users understand the reason for…

Information Retrieval · Computer Science 2023-06-02 Niloofar Ranjbar , Saeedeh Momtazi , MohammadMehdi Homayounpour

Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to change the visual decision of a model. Adversarial attacks…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Drew Linsley , Pinyuan Feng , Thibaut Boissin , Alekh Karkada Ashok , Thomas Fel , Stephanie Olaiya , Thomas Serre

This paper investigates the use of artificial neural networks (ANNs) to replace traditional algorithms and manual review for identifying anomalies in vehicle run data. The specific data used for this study is from undersea vehicle…

Neural and Evolutionary Computing · Computer Science 2016-03-17 Adam J. Last

With the rapid growth of the Internet of Things (IoT), integrating artificial intelligence (AI) on extremely weak embedded devices has garnered significant attention, enabling improved real-time performance and enhanced data privacy.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Jiaming Huang , Yi Gao , Fuchang Pan , Renjie Li , Wei Dong

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…

Machine Learning · Computer Science 2020-11-04 Tao Bai , Jinqi Luo , Jun Zhao

Recommender systems employ machine learning models to learn from historical data to predict the preferences of users. Deep neural network (DNN) models such as neural collaborative filtering (NCF) are increasingly popular. However, the…

Information Retrieval · Computer Science 2022-08-29 Gang Liu , Zhihan Zhang , Zheng Ning , Meng Jiang

Deep learning models suffer from the problem of semantic discontinuity: small perturbations in the input space tend to cause semantic-level interference to the model output. We argue that the semantic discontinuity results from these…

Machine Learning · Computer Science 2024-06-18 Shangxi Wu , Dongyuan Lu , Xian Zhao , Lizhang Chen , Jitao Sang

Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose…

Machine Learning · Computer Science 2025-07-09 Zhan Qu , Daniel Gomm , Michael Färber

Company financial risks pose a significant threat to personal wealth and national economic stability, stimulating increasing attention towards the development of efficient andtimely methods for monitoring them. Current approaches tend to…

Computational Engineering, Finance, and Science · Computer Science 2025-03-11 Huaming Du , Lei Yuan , Qing Yang , Xingyan Chen , Yu Zhao , Han Ji , Fuzhen Zhuang , Carl Yang , Gang Kou

While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that…

Computation and Language · Computer Science 2022-03-25 Linyi Yang , Jiazheng Li , Pádraig Cunningham , Yue Zhang , Barry Smyth , Ruihai Dong

Complex systems are fascinating because their rich macroscopic properties emerge from the interaction of many simple parts. Understanding the building principles of these emergent phenomena in nature requires assessing natural complex…

Neurons and Cognition · Quantitative Biology 2022-11-17 Anna Levina , Viola Priesemann , Johannes Zierenberg

This paper presents a novel method for discovering systematic errors in segmentation models. For instance, a systematic error in the segmentation model can be a sufficiently large number of misclassifications from the model as a parking…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Jaisidh Singh , Sonam Singh , Amit Arvind Kale , Harsh K Gandhi

Deep neural networks (DNNs) achieve state-of-the-art results in a variety of domains. Unfortunately, DNNs are notorious for their non-interpretability, and thus limit their applicability in hypothesis-driven domains such as biology and…

Machine Learning · Computer Science 2018-03-12 Chun-Hao Chang , Ladislav Rampasek , Anna Goldenberg

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

Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usually, this problem is…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Marvin Klingner , Mouadh Ayache , Tim Fingscheidt

Deep Neural Networks (DNNs) have demonstrated strong capacity in supporting a wide variety of applications. Shapley value has emerged as a prominent tool to analyze feature importance to help people understand the inference process of deep…

Machine Learning · Statistics 2025-02-19 Xiaolei Lu

Semantic annotations have to satisfy quality constraints to be useful for digital libraries, which is particularly challenging on large and diverse datasets. Confidence scores of multi-label classification methods typically refer only to…

Information Retrieval · Computer Science 2018-06-08 Martin Toepfer , Christin Seifert

Deep neural networks (DNNs) are now the de facto choice for computer vision tasks such as image classification. However, their complexity and "black box" nature often renders the systems they're deployed in vulnerable to a range of security…

Cryptography and Security · Computer Science 2021-10-19 Chandramouli Amarnath , Aishwarya H. Balwani , Kwondo Ma , Abhijit Chatterjee

Adversarial examples (AEs) pose severe threats to the applications of deep neural networks (DNNs) to safety-critical domains, e.g., autonomous driving. While there has been a vast body of AE defense solutions, to the best of our knowledge,…

Cryptography and Security · Computer Science 2022-01-25 Yijun Yang , Ruiyuan Gao , Yu Li , Qiuxia Lai , Qiang Xu