English
Related papers

Related papers: TaeBench: Improving Quality of Toxic Adversarial E…

200 papers

User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets will also tend to disregard context, making the detection of…

Computation and Language · Computer Science 2021-11-22 Alexandros Xenos , John Pavlopoulos , Ion Androutsopoulos , Lucas Dixon , Jeffrey Sorensen , Leo Laugier

Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples. In this paper, we present a novel training procedure and a thresholding test strategy, towards robust…

Machine Learning · Computer Science 2018-11-08 Tianyu Pang , Chao Du , Yinpeng Dong , Jun Zhu

Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness. Existing attacks are usually realized through word-level or…

Computation and Language · Computer Science 2022-05-25 Yibin Lei , Yu Cao , Dianqi Li , Tianyi Zhou , Meng Fang , Mykola Pechenizkiy

While the transferability property of adversarial examples allows the adversary to perform black-box attacks (i.e., the attacker has no knowledge about the target model), the transfer-based adversarial attacks have gained great attention.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Bin Chen , Jia-Li Yin , Shukai Chen , Bo-Hao Chen , Ximeng Liu

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

Adversarial examples, generated by applying small perturbations to input features, are widely used to fool classifiers and measure their robustness to noisy inputs. However, little work has been done to evaluate the robustness of ranking…

Information Retrieval · Computer Science 2020-08-06 Nisarg Raval , Manisha Verma

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

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

Recently, unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. Previous studies in unsupervised AT have mostly focused on implementing self-supervised…

Machine Learning · Computer Science 2023-10-27 Minseon Kim , Hyeonjeong Ha , Sooel Son , Sung Ju Hwang

Large language models (LLMs) require robust toxicity evaluation beyond explicit wording. This setting remains underexplored in Chinese, where toxicity may combine semantic indirectness with surface obfuscation. We introduce Chinese Implicit…

Computation and Language · Computer Science 2026-05-22 Jingyi Kang , Junyu Lu , Bo Xu , Hongbo Wang , Linlin zong , Roy Ka-Wei Lee , Hongfei Lin

In predictive process monitoring, predictive models are vulnerable to adversarial attacks, where input perturbations can lead to incorrect predictions. Unlike in computer vision, where these perturbations are designed to be imperceptible to…

Machine Learning · Computer Science 2024-11-22 Alexander Stevens , Jari Peeperkorn , Johannes De Smedt , Jochen De Weerdt

In this paper, we present an effective method to craft text adversarial samples, revealing one important yet underestimated fact that DNN-based text classifiers are also prone to adversarial sample attack. Specifically, confronted with…

Cryptography and Security · Computer Science 2019-01-08 Bin Liang , Hongcheng Li , Miaoqiang Su , Pan Bian , Xirong Li , Wenchang Shi

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…

Machine Learning · Computer Science 2021-09-15 Bin Zhu , Zhaoquan Gu , Le Wang , Zhihong Tian

Deep learning models have shown promising predictive accuracy for time-series healthcare applications. However, ensuring the robustness of these models is vital for building trustworthy AI systems. Existing research predominantly focuses on…

Machine Learning · Computer Science 2023-11-08 Sydney Pugh , Ivan Ruchkin , Insup Lee , James Weimer

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…

Machine Learning · Statistics 2025-07-10 Victor Gallego , Roi Naveiro , Alberto Redondo , David Rios Insua , Fabrizio Ruggeri

Current Machine Translation (MT) systems achieve very good results on a growing variety of language pairs and datasets. However, they are known to produce fluent translation outputs that can contain important meaning errors, thus…

Computation and Language · Computer Science 2021-09-23 Diptesh Kanojia , Marina Fomicheva , Tharindu Ranasinghe , Frédéric Blain , Constantin Orăsan , Lucia Specia

We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for…

Computation and Language · Computer Science 2018-05-15 Dongyeop Kang , Tushar Khot , Ashish Sabharwal , Eduard Hovy

We introduce Mischief, a simple and lightweight method to produce a class of human-readable, realistic adversarial examples for language models. We perform exhaustive experimentations of our algorithm on four transformer-based…

Computation and Language · Computer Science 2020-10-19 Adrian de Wynter

This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and non-mainstream language uses. We contribute two newly…

Computation and Language · Computer Science 2024-10-18 Xinmeng Hou

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…

Computation and Language · Computer Science 2024-01-09 Tom Roth , Yansong Gao , Alsharif Abuadbba , Surya Nepal , Wei Liu