English
Related papers

Related papers: White-box Testing of NLP models with Mask Neuron C…

200 papers

Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that assess model behavior…

Computers and Society · Computer Science 2026-05-19 Hannah Cyberey , Yangfeng Ji , David Evans

Deep neural networks (DNNs) have shown to perform very well on large scale object recognition problems and lead to widespread use for real-world applications, including situations where DNN are implemented as "black boxes". A promising…

Computer Vision and Pattern Recognition · Computer Science 2021-11-01 Federica Granese , Marco Romanelli , Daniele Gorla , Catuscia Palamidessi , Pablo Piantanida

Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear normal to human beings. Recent work has shown that pixel…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Pratik Vaishnavi , Tianji Cong , Kevin Eykholt , Atul Prakash , Amir Rahmati

In recent years, deep neural networks (DNNs) have shown competitive results in many fields. Despite this success, they often suffer from poor calibration, especially in safety-critical scenarios such as autonomous driving and healthcare,…

Machine Learning · Computer Science 2025-08-13 Jiani Ni , He Zhao , Yibo Yang , Dandan Guo

Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated, which can lead them to optimize for test-passing performance or to comply more readily with harmful prompts if real-world consequences…

Computation and Language · Computer Science 2025-10-29 Sahar Abdelnabi , Ahmed Salem

In deep learning (DL) systems, label noise in training datasets often degrades model performance, as models may learn incorrect patterns from mislabeled data. The area of Learning with Noisy Labels (LNL) has introduced methods to…

Machine Learning · Computer Science 2024-12-03 Gordon Lim , Stefan Larson , Kevin Leach

Recently, machine and deep learning (ML/DL) algorithms have been increasingly adopted in many software systems. Due to their inductive nature, ensuring the quality of these systems remains a significant challenge for the research community.…

Software Engineering · Computer Science 2024-07-16 Moses Openja , Foutse Khomh , Armstrong Foundjem , Zhen Ming , Jiang , Mouna Abidi , Ahmed E. Hassan

An important feature of successful supervised machine learning applications is to be able to explain the predictions given by the regression or classification model being used. However, most state-of-the-art models that have good predictive…

Machine Learning · Statistics 2019-10-14 Victor Coscrato , Marco Henrique de Almeida Inácio , Tiago Botari , Rafael Izbicki

Noisy labels are inevitable in real-world scenarios. Due to the strong capacity of deep neural networks to memorize corrupted labels, these noisy labels can cause significant performance degradation. Existing research on mitigating the…

Machine Learning · Computer Science 2025-10-02 Xinlei Zhang , Fan Liu , Chuanyi Zhang , Fan Cheng , Yuhui Zheng

Deep neural networks (DNNs) have demonstrated superior performance over classical machine learning to support many features in safety-critical systems. Although DNNs are now widely used in such systems (e.g., self driving cars), there is…

Software Engineering · Computer Science 2022-10-17 Mohammed Oualid Attaoui , Hazem Fahmy , Fabrizio Pastore , Lionel Briand

Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they…

Computer Vision and Pattern Recognition · Computer Science 2019-08-14 Moustafa Alzantot , Amy Widdicombe , Simon Julier , Mani Srivastava

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their…

Artificial Intelligence · Computer Science 2019-11-28 Vanessa Buhrmester , David Münch , Michael Arens

Channel Pruning has been long studied to compress CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while…

Computer Vision and Pattern Recognition · Computer Science 2022-01-31 Yuxin Zhang , Mingbao Lin , Chia-Wen Lin , Jie Chen , Feiyue Huang , Yongjian Wu , Yonghong Tian , Rongrong Ji

Testing with randomly generated inputs (fuzzing) has gained significant traction due to its capacity to expose program vulnerabilities automatically. Fuzz testing campaigns generate large amounts of data, making them ideal for the…

Software Engineering · Computer Science 2023-09-29 Maria-Irina Nicolae , Max Eisele , Andreas Zeller

Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability…

Machine Learning · Statistics 2015-08-31 Yanping Huang , Sai Zhang

Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious…

Machine Learning · Computer Science 2026-05-22 Yifan Lan , Yuanpu Cao , Hanyu Wang , Lu Lin , Jinghui Chen

Deep Neural Networks (DNN) have been widely employed in industry to address various Natural Language Processing (NLP) tasks. However, many engineers find it a big overhead when they have to choose from multiple frameworks, compare different…

Computation and Language · Computer Science 2019-10-21 Ming Gong , Linjun Shou , Wutao Lin , Zhijie Sang , Quanjia Yan , Ze Yang , Feixiang Cheng , Daxin Jiang

Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary…

Machine Learning · Statistics 2018-02-15 Seong Joon Oh , Max Augustin , Bernt Schiele , Mario Fritz

An exciting recent development is the uptake of deep neural networks in many scientific fields, where the main objective is outcome prediction with the black-box nature. Significance testing is promising to address the black-box issue and…

Machine Learning · Statistics 2022-06-22 Ben Dai , Xiaotong Shen , Wei Pan

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

Computation and Language · Computer Science 2024-03-19 Siwen Luo , Hamish Ivison , Caren Han , Josiah Poon
‹ Prev 1 3 4 5 6 7 10 Next ›