English
Related papers

Related papers: Certifying Out-of-Domain Generalization for Blackb…

200 papers

This article presents novel methods for synthesizing distributionally robust stabilizing neural controllers and certificates for control systems under model uncertainty. A key challenge in designing controllers with stability guarantees for…

Systems and Control · Electrical Eng. & Systems 2024-08-06 Kehan Long , Jorge Cortes , Nikolay Atanasov

To create state-of-the-art models for many downstream tasks, it has become common practice to fine-tune a pre-trained large vision model. However, it remains an open question of how to best determine which of the many possible model…

Machine Learning · Computer Science 2025-12-08 Simon Guiroy , Mats Richter , Sarath Chandar , Christopher Pal

Neural networks are highly effective tools for pose estimation. However, as in other computer vision tasks, robustness to out-of-domain data remains a challenge, especially for small training sets that are common for real-world…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Alexander Mathis , Thomas Biasi , Steffen Schneider , Mert Yüksekgönül , Byron Rogers , Matthias Bethge , Mackenzie W. Mathis

The black box nature of deep learning models complicate their usage in critical applications such as remote sensing. Conformal prediction is a method to ensure trust in such scenarios. Subject to data exchangeability, conformal prediction…

Machine Learning · Computer Science 2024-05-07 Protim Bhattacharjee , Peter Jung

In response to subtle adversarial examples flipping classifications of neural network models, recent research has promoted certified robustness as a solution. There, invariance of predictions to all norm-bounded attacks is achieved through…

Machine Learning · Computer Science 2022-10-13 Andrew C. Cullen , Paul Montague , Shijie Liu , Sarah M. Erfani , Benjamin I. P. Rubinstein

Despite apparent human-level performances of deep neural networks (DNN), they behave fundamentally differently from humans. They easily change predictions when small corruptions such as blur and noise are applied on the input (lack of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Sanghyuk Chun , Seong Joon Oh , Sangdoo Yun , Dongyoon Han , Junsuk Choe , Youngjoon Yoo

Sensitivity-based robustness certification has emerged as a practical approach for certifying neural network robustness, including in settings that require verifiable guarantees. A key advantage of these methods is that certification is…

Machine Learning · Computer Science 2026-03-26 Toby Murray

Software development in the aerospace domain requires adhering to strict, high-quality standards. While there exist regulatory guidelines for commercial software in this domain (e.g., ARP-4754 and DO-178), these do not apply to software…

Software Engineering · Computer Science 2024-08-06 Guy Katz , Natan Levy , Idan Refaeli , Raz Yerushalmi

Developing and deploying machine learning models safely depends on the ability to characterize and compare their abilities to generalize to new environments. Although recent work has proposed a variety of methods that can directly predict…

Machine Learning · Computer Science 2023-07-18 Nathan Ng , Neha Hulkund , Kyunghyun Cho , Marzyeh Ghassemi

The Newton method has been widely adopted to achieve certified unlearning. A critical assumption in existing approaches is that the data requested for unlearning are selected i.i.d.(independent and identically distributed). However,the…

Machine Learning · Computer Science 2026-01-13 Jinduo Guo , Yinzhi Cao

We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approaches do not provide…

Machine Learning · Computer Science 2025-11-11 Peter Blohm , Patrick Indri , Thomas Gärtner , Sagar Malhotra

Out-of-Distribution (OOD) generalization has become a primary metric for evaluating image analysis systems. Since deep learning models tend to capture domain-specific context, they often develop shortcut dependencies on these non-causal…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Haoran Pei , Yuguang Yang , Kexin Liu , Juan Zhang , Baochang Zhang

This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By training on…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Zhaodi Zhang , Zhiyi Xue , Yang Chen , Si Liu , Yueling Zhang , Jing Liu , Min Zhang

Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from…

Machine Learning · Computer Science 2021-03-16 Aristotelis-Angelos Papadopoulos , Mohammad Reza Rajati , Nazim Shaikh , Jiamian Wang

While recent advances in deep learning for surgical scene segmentation have demonstrated promising results on single-centre and single-imaging modality data, these methods usually do not generalise to unseen distribution (i.e., from other…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Mansoor Ali , Maksim Richards , Gilberto Ochoa-Ruiz , Sharib Ali

As training datasets grow larger, we aspire to develop models that generalize well to any diverse test distribution, even if the latter deviates significantly from the training data. Various approaches like domain adaptation, domain…

Machine Learning · Computer Science 2024-10-10 Andreas Loukas , Karolis Martinkus , Ed Wagstaff , Kyunghyun Cho

Patch robustness certification is an emerging kind of provable defense technique against adversarial patch attacks for deep learning systems. Certified detection ensures the detection of all patched harmful versions of certified samples,…

Software Engineering · Computer Science 2025-12-09 Qilin Zhou , Zhengyuan Wei , Haipeng Wang , Zhuo Wang , W. K. Chan

Calibration and uncertainty estimation are crucial topics in high-risk environments. We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples and increases the overall accuracy, calibration and…

Machine Learning · Computer Science 2022-10-21 Hendrik Alexander Mehrtens , Camila González , Anirban Mukhopadhyay

We address the challenge of certifying the performance of a federated learning model on an unseen target network using only measurements from the source network that trained the model. Specifically, consider a source network "A" with $K$…

Machine Learning · Statistics 2025-06-10 Amir Najafi , Samin Mahdizadeh Sani , Farzan Farnia

We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts via a differentiable density ratio…

Machine Learning · Computer Science 2024-02-07 Haoxuan Wang , Zhiding Yu , Yisong Yue , Anima Anandkumar , Anqi Liu , Junchi Yan