English
Related papers

Related papers: Enhancing Adversarial Text Attacks on BERT Models …

200 papers

Artificial neural networks in general and deep learning networks in particular established themselves as popular and powerful machine learning algorithms. While the often tremendous sizes of these networks are beneficial when solving…

Machine Learning · Computer Science 2020-05-28 Moritz Seiler , Heike Trautmann , Pascal Kerschke

Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples…

Computation and Language · Computer Science 2021-10-05 Wenqian Ye , Fei Xu , Yaojia Huang , Cassie Huang , Ji A

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

This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two…

Cryptography and Security · Computer Science 2025-09-19 Gustavo Sandoval , Denys Fenchenko , Junyao Chen

Pre-training models are an important tool in Natural Language Processing (NLP), while the BERT model is a classic pre-training model whose structure has been widely adopted by followers. It was even chosen as the reference model for the…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-18 Jinle Zeng , Min Li , Zhihua Wu , Jiaqi Liu , Yuang Liu , Dianhai Yu , Yanjun Ma

Adversarial Examples Detection (AED) is a crucial defense technique against adversarial attacks and has drawn increasing attention from the Natural Language Processing (NLP) community. Despite the surge of new AED methods, our studies show…

Computation and Language · Computer Science 2022-10-25 Fan Yin , Yao Li , Cho-Jui Hsieh , Kai-Wei Chang

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly…

Computation and Language · Computer Science 2022-05-02 Na Liu , Mark Dras , Wei Emma Zhang

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Cryptography and Security · Computer Science 2024-10-14 Xiaopei Zhu , Peiyang Xu , Guanning Zeng , Yingpeng Dong , Xiaolin Hu

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Cryptography and Security · Computer Science 2024-11-04 Qizhang Li , Yiwen Guo , Wangmeng Zuo , Hao Chen

Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet…

Machine Learning · Computer Science 2023-01-27 Jon Vadillo , Roberto Santana , Jose A. Lozano

In the past few years, it has become increasingly evident that deep neural networks are not resilient enough to withstand adversarial perturbations in input data, leaving them vulnerable to attack. Various authors have proposed strong…

Computation and Language · Computer Science 2023-04-19 Shreya Goyal , Sumanth Doddapaneni , Mitesh M. Khapra , Balaraman Ravindran

Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most…

Machine Learning · Computer Science 2023-10-26 Weimin Lyu , Songzhu Zheng , Lu Pang , Haibin Ling , Chao Chen

Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks.…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Mengting Xu , Tao Zhang , Zhongnian Li , Daoqiang Zhang

Pre-trained Language Models (PLMs) have achieved remarkable performance on diverse NLP tasks through pre-training and fine-tuning. However, fine-tuning the model with a large number of parameters on limited downstream datasets often leads…

Computation and Language · Computer Science 2025-05-13 Mihyeon Kim , Juhyoung Park , Youngbin Kim

Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gradient-based attacks). However, it is an open question…

Machine Learning · Computer Science 2019-06-07 Shiqi Wang , Yizheng Chen , Ahmed Abdou , Suman Jana

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient…

Machine Learning · Computer Science 2018-06-22 Ayan Sinha , Zhao Chen , Vijay Badrinarayanan , Andrew Rabinovich

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

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

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

Model inversion (MI) attacks have raised increasing concerns about privacy, which can reconstruct training data from public models. Indeed, MI attacks can be formalized as an optimization problem that seeks private data in a certain space.…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Xiaojian Yuan , Kejiang Chen , Jie Zhang , Weiming Zhang , Nenghai Yu , Yang Zhang