English
Related papers

Related papers: Input Prioritization for Testing Neural Networks

200 papers

As deep neural networks (DNNs) are increasingly used in safety-critical applications, there is a growing concern for their reliability. Even highly trained, high-performant networks are not 100% accurate. However, it is very difficult to…

Neural and Evolutionary Computing · Computer Science 2024-07-30 Eduard Pinconschi , Divya Gopinath , Rui Abreu , Corina S. Pasareanu

In safety-critical systems (e.g., autonomous vehicles and robots), Deep Neural Networks (DNNs) are becoming a key component for computer vision tasks, particularly semantic segmentation. Further, since the DNN behavior cannot be assessed…

Software Engineering · Computer Science 2025-03-21 Mohammed Oualid Attaoui , Fabrizio Pastore , Lionel Briand

Deep neural networks (DNNs) can easily fit a random labeling of the training data with zero training error. What is the difference between DNNs trained with random labels and the ones trained with true labels? Our paper answers this…

Machine Learning · Computer Science 2019-11-22 Jindong Gu , Volker Tresp

Deep neural networks (DNNs) have become an enabling component for a myriad of artificial intelligence applications. DNNs have shown sometimes superior performance, even compared to humans, in cases such as self-driving, health applications,…

Neural and Evolutionary Computing · Computer Science 2023-07-12 Ghada Alsuhli , Vasileios Sakellariou , Hani Saleh , Mahmoud Al-Qutayri , Baker Mohammad , Thanos Stouraitis

Deep neural networks (DNNs) are instrumental in realizing complex perception systems. As many of these applications are safety-critical by design, engineering rigor is required to ensure that the functional insufficiency of the DNN-based…

Machine Learning · Computer Science 2023-10-09 Chih-Hong Cheng , Michael Luttenberger , Rongjie Yan

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Matthias Rottmann , Marco Reese

In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks. With the broader deployment of DNNs on various applications, the concerns over…

Machine Learning · Computer Science 2020-06-02 Xiaowei Huang , Daniel Kroening , Wenjie Ruan , James Sharp , Youcheng Sun , Emese Thamo , Min Wu , Xinping Yi

When employing deep neural networks (DNNs) for semantic segmentation in safety-critical applications like automotive perception or medical imaging, it is important to estimate their performance at runtime, e.g. via uncertainty estimates or…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Edgar Heinert , Stephan Tilgner , Timo Palm , Matthias Rottmann

The widespread adoption of deep neural networks (DNNs) requires efficient techniques for verifying their safety. DNN verifiers are complex tools, which might contain bugs that could compromise their soundness and undermine the reliability…

Logic in Computer Science · Computer Science 2025-11-12 Omri Isac , Idan Refaeli , Haoze Wu , Clark Barrett , Guy Katz

The growing prosperity of social networks has brought great challenges to the sentimental tendency mining of users. As more and more researchers pay attention to the sentimental tendency of online users, rich research results have been…

Computation and Language · Computer Science 2019-07-04 Donghang Pan , Jingling Yuan , Lin Li , Deming Sheng

Binary Neural Networks (BNNs) have emerged as a promising solution for reducing the memory footprint and compute costs of deep neural networks, but they suffer from quality degradation due to the lack of freedom as activations and weights…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Changhun Lee , Hyungjun Kim , Eunhyeok Park , Jae-Joon Kim

Unregularized deep neural networks (DNNs) can be easily overfit with a limited sample size. We argue that this is mostly due to the disriminative nature of DNNs which directly model the conditional probability (or score) of labels given the…

Machine Learning · Computer Science 2016-01-11 Shuangfei Zhai , Zhongfei Zhang

Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at…

Computer Vision and Pattern Recognition · Computer Science 2017-08-15 Vivienne Sze , Yu-Hsin Chen , Tien-Ju Yang , Joel Emer

There is a growing body of research on developing testing techniques for Deep Neural Networks (DNN). We distinguish two general modes of testing for DNNs: Offline testing where DNNs are tested as individual units based on test datasets…

Machine Learning · Computer Science 2021-05-03 Fitash Ul Haq , Donghwan Shin , Shiva Nejati , Lionel Briand

Graph neural network-based network intrusion detection systems have recently demonstrated state-of-the-art performance on benchmark datasets. Nevertheless, these methods suffer from a reliance on target encoding for data pre-processing,…

Cryptography and Security · Computer Science 2024-03-01 Zhengyao Gu , Diego Troy Lopez , Lilas Alrahis , Ozgur Sinanoglu

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of…

Computation and Language · Computer Science 2019-09-04 Hao Wang , Bing Liu , Chaozhuo Li , Yan Yang , Tianrui Li

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Machine Learning · Computer Science 2021-06-03 Omer Faruk Tuna , Ferhat Ozgur Catak , M. Taner Eskil

We distinguish two general modes of testing for Deep Neural Networks (DNNs): Offline testing where DNNs are tested as individual units based on test datasets obtained without involving the DNNs under test, and online testing where DNNs are…

Software Engineering · Computer Science 2022-01-31 Fitash Ul Haq , Donghwan Shin , Shiva Nejati , Lionel Briand

Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals. Provided the intractably large size of such input spaces, the…

Software Engineering · Computer Science 2021-02-03 Michael Weiss , Paolo Tonella

To improve trust and transparency, it is crucial to be able to interpret the decisions of Deep Neural classifiers (DNNs). Instance-level examinations, such as attribution techniques, are commonly employed to interpret the model decisions.…

Machine Learning · Computer Science 2025-03-13 Youngju Joung , Sehyun Lee , Jaesik Choi