English
Related papers

Related papers: BERT-ATTACK: Adversarial Attack Against BERT Using…

200 papers

Large language models have many beneficial applications, but can they also be used to attack content-filtering algorithms in social media platforms? We investigate the challenge of generating adversarial examples to test the robustness of…

Computation and Language · Computer Science 2025-09-04 Piotr Przybyła , Euan McGill , Horacio Saggion

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However,…

Computation and Language · Computer Science 2021-10-07 Zongyi Li , Jianhan Xu , Jiehang Zeng , Linyang Li , Xiaoqing Zheng , Qi Zhang , Kai-Wei Chang , Cho-Jui Hsieh

Pretrained contextualized language models such as BERT have achieved impressive results on various natural language processing benchmarks. Benefiting from multiple pretraining tasks and large scale training corpora, pretrained models can…

Information Retrieval · Computer Science 2020-05-28 Zhiyu Chen , Mohamed Trabelsi , Jeff Heflin , Yinan Xu , Brian D. Davison

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has explored adversarial training techniques, their improvements…

Computation and Language · Computer Science 2024-03-28 Brian Formento , Wenjie Feng , Chuan Sheng Foo , Luu Anh Tuan , See-Kiong Ng

Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…

Computer Vision and Pattern Recognition · Computer Science 2019-08-19 Ameya Joshi , Amitangshu Mukherjee , Soumik Sarkar , Chinmay Hegde

Sequence-based deep learning models (e.g., RNNs), can detect malware by analyzing its behavioral sequences. Meanwhile, these models are susceptible to adversarial attacks. Attackers can create adversarial samples that alter the sequence…

Cryptography and Security · Computer Science 2025-09-16 Kai Tan , Dongyang Zhan , Lin Ye , Hongli Zhang , Binxing Fang

Offensive language detection is an ever-growing natural language processing (NLP) application. This growth is mainly because of the widespread usage of social networks, which becomes a mainstream channel for people to communicate, work, and…

Computation and Language · Computer Science 2021-06-29 Ehab Hamdy

The widespread use of text-based communication on social media-through chats, comments, and microblogs-has improved user interaction but has also led to an increase in offensive content, including hate speech, racism, and other forms of…

Computation and Language · Computer Science 2025-06-30 Reem Alothman , Hafida Benhidour , Said Kerrache

Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by…

Machine Learning · Computer Science 2019-03-19 Ping Yu , Kaitao Song , Jianfeng Lu

It is challenging to control the quality of online information due to the lack of supervision over all the information posted online. Manual checking is almost impossible given the vast number of posts made on online media and how quickly…

Computation and Language · Computer Science 2022-03-16 Rini Anggrainingsih , Ghulam Mubashar Hassan , Amitava Datta

For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…

Computer Vision and Pattern Recognition · Computer Science 2019-08-29 Nikolaos Sarafianos , Xiang Xu , Ioannis A. Kakadiaris

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

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Computation and Language · Computer Science 2021-12-23 Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models.…

Computation and Language · Computer Science 2018-12-18 Xing Wu , Shangwen Lv , Liangjun Zang , Jizhong Han , Songlin Hu

Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to…

Computation and Language · Computer Science 2023-07-25 Neel Bhandari , Pin-Yu Chen

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…

Computer Vision and Pattern Recognition · Computer Science 2019-11-25 Haichao Zhang , Jianyu Wang

Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to…

Computation and Language · Computer Science 2021-10-15 Fanchao Qi , Yangyi Chen , Xurui Zhang , Mukai Li , Zhiyuan Liu , Maosong Sun

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…

Computation and Language · Computer Science 2023-05-29 Xuanli He , Jun Wang , Benjamin Rubinstein , Trevor Cohn

The content on the web is in a constant state of flux. New entities, issues, and ideas continuously emerge, while the semantics of the existing conversation topics gradually shift. In recent years, pre-trained language models like BERT…

Computation and Language · Computer Science 2021-06-14 Spurthi Amba Hombaiah , Tao Chen , Mingyang Zhang , Michael Bendersky , Marc Najork