English
Related papers

Related papers: A Grey-box Text Attack Framework using Explainable…

200 papers

Black-box adversarial attack has attracted a lot of research interests for its practical use in AI safety. Compared with the white-box attack, a black-box setting is more difficult for less available information related to the attacked…

Machine Learning · Computer Science 2020-09-02 Linjun Zhou , Peng Cui , Yinan Jiang , Shiqiang Yang

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing, and scientific problem-solving. However, this progress has…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Jindong Gu , Xiaojun Jia , Pau de Jorge , Wenqain Yu , Xinwei Liu , Avery Ma , Yuan Xun , Anjun Hu , Ashkan Khakzar , Zhijiang Li , Xiaochun Cao , Philip Torr

Deep learning models are susceptible to adversarial examples that have imperceptible perturbations in the original input, resulting in adversarial attacks against these models. Analysis of these attacks on the state of the art transformers…

Computation and Language · Computer Science 2021-01-22 Vijit Malik , Ashwani Bhat , Ashutosh Modi

In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly…

Computation and Language · Computer Science 2022-11-08 Javier Ferrando , Gerard I. Gállego , Belen Alastruey , Carlos Escolano , Marta R. Costa-jussà

Transferable attacks generate adversarial examples on surrogate models to fool unknown victim models, posing real-world threats and growing research interest. Despite focusing on flat losses for transferable adversarial examples, recent…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Zhixuan Zhang , Pingyu Wang , Xingjian Zheng , Linbo Qing , Qi Liu

Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial…

Machine Learning · Computer Science 2024-04-18 Md Athikul Islam , Edoardo Serra , Sushil Jajodia

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Cryptography and Security · Computer Science 2023-05-01 Jiazhao Li , Yijin Yang , Zhuofeng Wu , V. G. Vinod Vydiswaran , Chaowei Xiao

Neural Machine Translation systems are used in diverse applications due to their impressive performance. However, recent studies have shown that these systems are vulnerable to carefully crafted small perturbations to their inputs, known as…

Computation and Language · Computer Science 2024-11-20 Sahar Sadrizadeh , César Descalzo , Ljiljana Dolamic , Pascal Frossard

Generative models, especially large language models (LLMs), have shown remarkable progress in producing text that appears human-like. However, they often exhibit patterns that make their output easier to detect than text written by humans.…

Computation and Language · Computer Science 2026-01-06 Hadi Mohammadi , Anastasia Giachanou , Daniel L. Oberski , Ayoub Bagheri

Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting,…

Computation and Language · Computer Science 2023-03-14 Hai Zhu , Qingyang Zhao , Yuren Wu

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 black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models. In this paper, we…

Machine Learning · Computer Science 2017-12-29 Arjun Nitin Bhagoji , Warren He , Bo Li , Dawn Song

A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and…

Machine Learning · Computer Science 2022-03-17 Nicholas A. Lord , Romain Mueller , Luca Bertinetto

Despite its significant benefits in enhancing the transparency and trustworthiness of artificial intelligence (AI) systems, explainable AI (XAI) has yet to reach its full potential in real-world applications. One key challenge is that XAI…

Machine Learning · Computer Science 2024-09-16 Kiana Vu , Phung Lai , Truc Nguyen

Neural text detectors aim to decide the characteristics that distinguish neural (machine-generated) from human texts. To challenge such detectors, adversarial attacks can alter the statistical characteristics of the generated text, making…

Cryptography and Security · Computer Science 2023-02-14 Gongbo Liang , Jesus Guerrero , Izzat Alsmadi

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

Machine Learning · Computer Science 2024-09-09 Hanbin Hong , Xinyu Zhang , Binghui Wang , Zhongjie Ba , Yuan Hong

Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enhance adversarial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Bohan Liu , Xiaosen Wang

There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously. It is unclear, however, how the models will perform in realistic scenarios…

Computation and Language · Computer Science 2020-03-12 Lichao Sun , Kazuma Hashimoto , Wenpeng Yin , Akari Asai , Jia Li , Philip Yu , Caiming Xiong

Neural networks are vulnerable to adversarial examples, which are malicious inputs crafted to fool pre-trained models. Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted…

Computer Vision and Pattern Recognition · Computer Science 2020-03-04 ZhaoXin Huan , Yulong Wang , Xiaolu Zhang , Lin Shang , Chilin Fu , Jun Zhou

Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Zhijin Ge , Fanhua Shang , Hongying Liu , Yuanyuan Liu , Liang Wan , Wei Feng , Xiaosen Wang