中文
相关论文

相关论文: The Pitfalls and Promise of Conformal Inference Un…

200 篇论文

As deep learning models are increasingly deployed in high-risk applications, robust defenses against adversarial attacks and reliable performance guarantees become paramount. Moreover, accuracy alone does not provide sufficient assurance or…

机器学习 · 计算机科学 2025-06-10 Jie Bao , Chuangyin Dang , Rui Luo , Hanwei Zhang , Zhixin Zhou

Conformal prediction (CP) provides distribution-free, finite-sample coverage guarantees but critically relies on exchangeability, a condition often violated under distribution shift. We study the robustness of split conformal prediction…

机器学习 · 统计学 2025-12-23 Xunlei Qian , Yue Xing

Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…

计算机视觉与模式识别 · 计算机科学 2022-12-07 Julia Grabinski , Paul Gavrikov , Janis Keuper , Margret Keuper

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…

机器学习 · 计算机科学 2022-06-15 Kaustubh Sridhar , Souradeep Dutta , Ramneet Kaur , James Weimer , Oleg Sokolsky , Insup Lee

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT…

机器学习 · 计算机科学 2020-04-14 Haidong Xie , Xueshuang Xiang , Naijin Liu , Bin Dong

Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfitting, i.e., the robustness starts to decrease significantly…

机器学习 · 计算机科学 2021-12-23 Jihoon Tack , Sihyun Yu , Jongheon Jeong , Minseon Kim , Sung Ju Hwang , Jinwoo Shin

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

机器学习 · 计算机科学 2024-10-22 Mengnan Zhao , Lihe Zhang , Jingwen Ye , Huchuan Lu , Baocai Yin , Xinchao Wang

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks.…

计算机视觉与模式识别 · 计算机科学 2025-11-04 Xin Liu , Yichen Yang , Kun He , John E. Hopcroft

Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained by different strategies. By revisiting the previous methods,…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Xingbin Liu , Huafeng Kuang , Xianming Lin , Yongjian Wu , Rongrong Ji

The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending attacks constrained within low magnitude Lp norm bounds,…

机器学习 · 计算机科学 2022-10-19 Sravanti Addepalli , Samyak Jain , Gaurang Sriramanan , R. Venkatesh Babu

Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…

机器学习 · 计算机科学 2021-10-13 Tianjin Huang , Vlado Menkovski , Yulong Pei , Mykola Pechenizkiy

It has been consistently reported that many machine learning models are susceptible to adversarial attacks i.e., small additive adversarial perturbations applied to data points can cause misclassification. Adversarial training using…

机器学习 · 统计学 2021-07-15 Hossein Taheri , Ramtin Pedarsani , Christos Thrampoulidis

Deep learning models have a propensity for fitting the entire training set even with random labels, which requires memorization of every training sample. In this paper, we explore the memorization effect in adversarial training (AT) for…

机器学习 · 计算机科学 2022-03-15 Yinpeng Dong , Ke Xu , Xiao Yang , Tianyu Pang , Zhijie Deng , Hang Su , Jun Zhu

Recent improvements in deep learning models and their practical applications have raised concerns about the robustness of these models against adversarial examples. Adversarial training (AT) has been shown effective to reach a robust model…

机器学习 · 计算机科学 2021-03-30 Mohammad Azizmalayeri , Mohammad Hossein Rohban

Deep learning has achieved great success in computer vision, but remains vulnerable to adversarial attacks. Adversarial training is the leading defense designed to improve model robustness. However, its effect on the transferability of…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Mohamed Awad , Mahmoud Akrm , Walid Gomaa

Conformal prediction (CP) is a framework to quantify uncertainty of machine learning classifiers including deep neural networks. Given a testing example and a trained classifier, CP produces a prediction set of candidate labels with a…

机器学习 · 计算机科学 2023-08-01 Subhankar Ghosh , Yuanjie Shi , Taha Belkhouja , Yan Yan , Jana Doppa , Brian Jones

Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations.…

机器学习 · 计算机科学 2020-07-01 David Stutz , Matthias Hein , Bernt Schiele

We investigate the integration of Conformal Prediction (CP) with supervised learning on deterministically encrypted data, aiming to bridge the gap between rigorous uncertainty quantification and privacy-preserving machine learning. Using…

机器学习 · 计算机科学 2025-07-15 Alexander David Balinsky , Dominik Krzeminski , Alexander Balinsky

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Yanyun Wang , Li Liu

Modern deep learning based classifiers show very high accuracy on test data but this does not provide sufficient guarantees for safe deployment, especially in high-stake AI applications such as medical diagnosis. Usually, predictions are…

机器学习 · 计算机科学 2022-05-09 David Stutz , Krishnamurthy , Dvijotham , Ali Taylan Cemgil , Arnaud Doucet
‹ 上一页 1 2 3 10 下一页 ›