English
Related papers

Related papers: Making Attention Mechanisms More Robust and Interp…

200 papers

Self-supervised learning methods for computer vision have demonstrated the effectiveness of pre-training feature representations, resulting in well-generalizing Deep Neural Networks, even if the annotated data are limited. However,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Dmitrii Shubin , Danny Eytan , Sebastian D. Goodfellow

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training…

Computation and Language · Computer Science 2022-03-25 Hanjie Chen , Yangfeng Ji

Vision transformer (ViT) models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains such as medical applications, autonomous vehicles, drones,…

Cryptography and Security · Computer Science 2025-07-22 Eldor Abdukhamidov , Mohammed Abuhamad , Simon S. Woo , Hyoungshick Kim , Tamer Abuhmed

Compared with standard supervised learning, the key difficulty in semi-supervised learning is how to make full use of the unlabeled data. A recently proposed method, virtual adversarial training (VAT), smartly performs adversarial training…

Machine Learning · Computer Science 2019-03-04 Bing Yu , Jingfeng Wu , Jinwen Ma , Zhanxing Zhu

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…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Julia Grabinski , Paul Gavrikov , Janis Keuper , Margret Keuper

Self-attention heads are characteristic of Transformer models and have been well studied for interpretability and pruning. In this work, we demonstrate an altogether different utility of attention heads, namely for adversarial detection.…

Computation and Language · Computer Science 2022-03-24 Emil Biju , Anirudh Sriram , Pratyush Kumar , Mitesh M Khapra

The vulnerability of deep neural networks (DNNs) to adversarial attack, which is an attack that can mislead state-of-the-art classifiers into making an incorrect classification with high confidence by deliberately perturbing the original…

Machine Learning · Computer Science 2021-06-18 Lina Wang , Rui Tang , Yawei Yue , Xingshu Chen , Wei Wang , Yi Zhu , Xuemei Zeng

The high cost of data labeling often results in node label shortage in real applications. To improve node classification accuracy, graph-based semi-supervised learning leverages the ample unlabeled nodes to train together with the scarce…

Machine Learning · Computer Science 2023-03-14 Jiaren Xiao , Quanyu Dai , Xiaochen Xie , James Lam , Ka-Wai Kwok

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian…

Machine Learning · Computer Science 2023-02-09 Boqi Li , Weiwei Liu

In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algorithms, IAT…

Computation and Language · Computer Science 2021-06-01 Wangchunshu Zhou , Qifei Li , Chenle Li

A major challenge for Multi-Agent Systems is enabling agents to adapt dynamically to diverse environments in which opponents and teammates may continually change. Agents trained using conventional methods tend to excel only within the…

Artificial Intelligence · Computer Science 2025-04-09 Qian Long , Ruoyan Li , Minglu Zhao , Tao Gao , Demetri Terzopoulos

Adversarial Training (AT) effectively improves the robustness of Deep Neural Networks (DNNs) to adversarial attacks. Generally, AT involves training DNN models with adversarial examples obtained within a pre-defined, fixed perturbation…

Machine Learning · Computer Science 2024-03-08 Olukorede Fakorede , Modeste Atsague , Jin Tian

Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model. In this paper, we introduce ACT, a novel adversarial attack…

Computation and Language · Computer Science 2024-02-23 Sahar Sadrizadeh , Ljiljana Dolamic , Pascal Frossard

Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by…

Machine Learning · Computer Science 2024-12-25 Bhavna Gopal , Huanrui Yang , Jingyang Zhang , Mark Horton , Yiran Chen

DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC model based on an…

Machine Learning · Computer Science 2025-01-06 Amirmohammad Bamdad , Ali Owfi , Fatemeh Afghah

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Tanmay Garg , Deepika Vemuri , Vineeth N Balasubramanian

Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…

Machine Learning · Computer Science 2025-05-20 Hana Satou , Alan Mitkiy

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Katarzyna Filus , Jorge M. Cruz-Duarte

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Yu Zhang , Zhiqiang Gong , Yichuang Zhang , YongQian Li , Kangcheng Bin , Jiahao Qi , Wei Xue , Ping Zhong

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

Computation and Language · Computer Science 2020-07-31 Xin Dong , Yaxin Zhu , Yupeng Zhang , Zuohui Fu , Dongkuan Xu , Sen Yang , Gerard de Melo