English
Related papers

Related papers: Interpretable Adversarial Training for Text

200 papers

Adversarial attacks pose a severe security threat to the state-of-the-art speaker identification systems, thereby making it vital to propose countermeasures against them. Building on our previous work that used representation learning to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Sonal Joshi , Saurabh Kataria , Jesus Villalba , Najim Dehak

This work proposes a novel algorithm to generate natural language adversarial input for text classification models, in order to investigate the robustness of these models. It involves applying gradient-based perturbation on the sentence…

Information Retrieval · Computer Science 2019-09-11 Yu-Lun Hsieh , Minhao Cheng , Da-Cheng Juan , Wei Wei , Wen-Lian Hsu , Cho-Jui Hsieh

Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a domain gap between the synthetic data and real data, which…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Mingkun Yang , Minghui Liao , Pu Lu , Jing Wang , Shenggao Zhu , Hualin Luo , Qi Tian , Xiang Bai

Gradient-based adversarial training is widely used in improving the robustness of neural networks, while it cannot be easily adapted to natural language processing tasks since the embedding space is discrete. In natural language processing…

Computation and Language · Computer Science 2020-12-07 Linyang Li , Xipeng Qiu

Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are…

Computation and Language · Computer Science 2021-04-22 Wenqi Wang , Run Wang , Lina Wang , Zhibo Wang , Aoshuang Ye

With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…

Computation and Language · Computer Science 2019-04-12 Wei Emma Zhang , Quan Z. Sheng , Ahoud Alhazmi , Chenliang Li

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Machine Learning · Computer Science 2019-10-08 Yulong Wang , Xiaolin Hu , Hang Su

Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning and data mining community. Being difficult to distinguish from real…

Machine Learning · Computer Science 2016-03-03 Chunchuan Lyu , Kaizhu Huang , Hai-Ning Liang

The paradigm of Differentially Private SGD~(DP-SGD) can provide a theoretical guarantee for training data in both centralized and federated settings. However, the utility degradation caused by DP-SGD limits its wide application in…

Cryptography and Security · Computer Science 2025-04-15 Haichao Sha , Ruixuan Liu , Yixuan Liu , Hong Chen

It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are…

Machine Learning · Computer Science 2018-10-25 Mohammad Hashemi , Greg Cusack , Eric Keller

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

In recent years, text generation tools utilizing Artificial Intelligence (AI) have occasionally been misused across various domains, such as generating student reports or creative writings. This issue prompts plagiarism detection services…

Computation and Language · Computer Science 2025-04-14 Ahmed K. Kadhim , Lei Jiao , Rishad Shafik , Ole-Christoffer Granmo

Synchronous stochastic gradient descent (SGD) is the most common method used for distributed training of deep learning models. In this algorithm, each worker shares its local gradients with others and updates the parameters using the…

Machine Learning · Computer Science 2020-09-22 Negar Foroutan Eghlidi , Martin Jaggi

Transferability, the ability of adversarial examples crafted for one model to deceive other models, is crucial for black-box attacks. Despite advancements in attack methods for semantic segmentation, transferability remains limited,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Eun-Sol Park , MiSo Park , Seung Park , Yong-Goo Shin

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Omid Poursaeed , Tianxing Jiang , Harry Yang , Serge Belongie , SerNam Lim

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Machine Learning · Computer Science 2019-09-10 Dilin Wang , Chengyue Gong , Qiang Liu

Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial…

Machine Learning · Computer Science 2020-01-29 Kazuya Kakizaki , Kosuke Yoshida

The effects of adversarial training on semantic segmentation networks has not been thoroughly explored. While previous work has shown that adversarially-trained image classifiers can be used to perform image synthesis, we have yet to…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Pedro Sandoval-Segura

Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from the underlying manifold of normal texts, whereas pre-trained…

Computation and Language · Computer Science 2025-04-15 Xiaomei Zhang , Zhaoxi Zhang , Yanjun Zhang , Xufei Zheng , Leo Yu Zhang , Shengshan Hu , Shirui Pan

We propose to adapt segmentation networks with a constrained formulation, which embeds domain-invariant prior knowledge about the segmentation regions. Such knowledge may take the form of simple anatomical information, e.g., structure size…

Computer Vision and Pattern Recognition · Computer Science 2021-04-13 Mathilde Bateson , Jose Dolz , Hoel Kervadec , Hervé Lombaert , Ismail Ben Ayed