English
Related papers

Related papers: How Does Adversarial Fine-Tuning Benefit BERT?

200 papers

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…

Machine Learning · Computer Science 2021-10-13 Tianjin Huang , Vlado Menkovski , Yulong Pei , Mykola Pechenizkiy

This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrades the standard…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Satoshi Suzuki , Shin'ya Yamaguchi , Shoichiro Takeda , Sekitoshi Kanai , Naoki Makishima , Atsushi Ando , Ryo Masumura

In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the…

Computation and Language · Computer Science 2018-10-02 Lijun Wu , Yingce Xia , Li Zhao , Fei Tian , Tao Qin , Jianhuang Lai , Tie-Yan Liu

Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the…

Machine Learning · Statistics 2020-07-06 Yifei Wang , Dan Peng , Furui Liu , Zhenguo Li , Zhitang Chen , Jiansheng Yang

Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains from AT on some tasks, e.g. commonsense reasoning, named…

Computation and Language · Computer Science 2023-05-09 Hongqiu Wu , Yongxiang Liu , Hanwen Shi , Hai Zhao , Min Zhang

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

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.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Xin Liu , Yichen Yang , Kun He , John E. Hopcroft

Adversarial training has been proven to be an effective technique for improving the adversarial robustness of models. However, there seems to be an inherent trade-off between optimizing the model for accuracy and robustness. To this end, we…

Computer Vision and Pattern Recognition · Computer Science 2020-08-20 Elahe Arani , Fahad Sarfraz , Bahram Zonooz

Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…

Computation and Language · Computer Science 2020-04-24 Chen Zhu , Yu Cheng , Zhe Gan , Siqi Sun , Tom Goldstein , Jingjing Liu

Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense.…

Machine Learning · Computer Science 2020-09-11 Theodoros Tsiligkaridis , Jay Roberts

For years, adversarial training has been extensively studied in natural language processing (NLP) settings. The main goal is to make models robust so that similar inputs derive in semantically similar outcomes, which is not a trivial…

Computation and Language · Computer Science 2021-09-21 Daniela N. Rim , DongNyeong Heo , Heeyoul Choi

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

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

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

Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a…

Machine Learning · Computer Science 2022-10-05 Chaojian Yu , Dawei Zhou , Li Shen , Jun Yu , Bo Han , Mingming Gong , Nannan Wang , Tongliang Liu

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…

Machine Learning · Statistics 2021-11-17 Takeru Miyato , Andrew M. Dai , Ian Goodfellow

Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm,…

Machine Learning · Computer Science 2020-02-19 Minhao Cheng , Qi Lei , Pin-Yu Chen , Inderjit Dhillon , Cho-Jui Hsieh

Contextual word embeddings (e.g. GPT, BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs very well in zero-shot and…

Computation and Language · Computer Science 2020-03-23 Phillip Keung , Yichao Lu , Vikas Bhardwaj

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur…

Computation and Language · Computer Science 2022-11-01 Hannah Chen , Yangfeng Ji , David Evans

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…

Cryptography and Security · Computer Science 2025-07-30 Stephen Casper , Lennart Schulze , Oam Patel , Dylan Hadfield-Menell