English
Related papers

Related papers: Generating Natural Language Attacks in a Hard Labe…

200 papers

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Machine Learning · Computer Science 2024-10-28 Samuel Jacob Chacko , Sajib Biswas , Chashi Mahiul Islam , Fatema Tabassum Liza , Xiuwen Liu

Recent studies have revealed the vulnerability of large language models to adversarial attacks, where adversaries craft specific input sequences to induce harmful, violent, private, or incorrect outputs. In this work, we study their…

Machine Learning · Computer Science 2025-10-09 Huanran Chen , Yinpeng Dong , Zeming Wei , Hang Su , Jun Zhu

Large language models play a crucial role in modern natural language processing technologies. However, their extensive use also introduces potential security risks, such as the possibility of black-box attacks. These attacks can embed…

Computation and Language · Computer Science 2025-02-25 Daniil Khomsky , Narek Maloyan , Bulat Nutfullin

With further development in the fields of computer vision, network security, natural language processing and so on so forth, deep learning technology gradually exposed certain security risks. The existing deep learning algorithms cannot…

Cryptography and Security · Computer Science 2020-11-18 Rui Zhao

Black-box adversarial attacks generate adversarial samples via iterative optimizations using repeated queries. Defending deep neural networks against such attacks has been challenging. In this paper, we propose an efficient Boundary Defense…

Cryptography and Security · Computer Science 2022-02-01 Manjushree B. Aithal , Xiaohua Li

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Machine Learning · Computer Science 2025-02-11 Brian Formento , Chuan Sheng Foo , See-Kiong Ng

Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these works do not accurately…

Machine Learning · Computer Science 2023-04-04 Jérôme Rony , Jean-Christophe Pesquet , Ismail Ben Ayed

The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Sampriti Soor , Alik Pramanick , Jothiprakash K , Arijit Sur

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

Computation and Language · Computer Science 2022-03-04 KiYoon Yoo , Jangho Kim , Jiho Jang , Nojun Kwak

Modern machine learning models with very high accuracy have been shown to be vulnerable to small, adversarially chosen perturbations of the input. Given black-box access to a high-accuracy classifier $f$, we show how to construct a new…

Machine Learning · Computer Science 2019-12-17 Grzegorz Głuch , Rüdiger Urbanke

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations.…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Tao Xiang , Hangcheng Liu , Shangwei Guo , Tianwei Zhang , Xiaofeng Liao

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception,…

Cryptography and Security · Computer Science 2025-07-23 Eldor Abdukhamidov , Tamer Abuhmed , Joanna C. S. Santos , Mohammed Abuhamad

With the rapid development of Deep Neural Networks (DNNs), they have been applied in numerous fields. However, research indicates that DNNs are susceptible to adversarial examples, and this is equally true in the multi-label domain. To…

Artificial Intelligence · Computer Science 2024-09-27 Yujiang Liu , Wenjian Luo , Zhijian Chen , Muhammad Luqman Naseem

Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models. Despite recent progress, existing approaches face two key limitations: (1) they overlook the critical…

Machine Learning · Computer Science 2026-05-25 Jun Liu , Leo Yu Zhang , Fengpeng Li , Isao Echizen , Jiantao Zhou

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning. We create a…

Computation and Language · Computer Science 2022-05-25 Zhao Meng , Yihan Dong , Mrinmaya Sachan , Roger Wattenhofer

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object…

Computer Vision and Pattern Recognition · Computer Science 2020-10-28 Quanyu Liao , Xin Wang , Bin Kong , Siwei Lyu , Youbing Yin , Qi Song , Xi Wu

Adversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can be…

Computation and Language · Computer Science 2020-10-07 Boxin Wang , Hengzhi Pei , Boyuan Pan , Qian Chen , Shuohang Wang , Bo Li

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include…

Cryptography and Security · Computer Science 2017-03-21 Nicolas Papernot , Patrick McDaniel , Ian Goodfellow , Somesh Jha , Z. Berkay Celik , Ananthram Swami

Face recognition has obtained remarkable progress in recent years due to the great improvement of deep convolutional neural networks (CNNs). However, deep CNNs are vulnerable to adversarial examples, which can cause fateful consequences in…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Yinpeng Dong , Hang Su , Baoyuan Wu , Zhifeng Li , Wei Liu , Tong Zhang , Jun Zhu

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…

Computation and Language · Computer Science 2025-04-22 Zhengxian Wu , Juan Wen , Wanli Peng , Ziwei Zhang , Yinghan Zhou , Yiming Xue