English
Related papers

Related papers: Reevaluating Adversarial Examples in Natural Langu…

200 papers

We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…

Machine Learning · Computer Science 2022-03-22 Johannes Schneider , Giovanni Apruzzese

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Computation and Language · Computer Science 2021-09-06 Paul Michel

Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed…

Machine Learning · Statistics 2015-03-24 Ian J. Goodfellow , Jonathon Shlens , Christian Szegedy

We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic questions posed in natural language, with an arbitrary…

In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side. Especially, there exists few…

Computation and Language · Computer Science 2021-06-16 Xiaosen Wang , Hao Jin , Yichen Yang , Kun He

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most…

Computation and Language · Computer Science 2021-06-01 Rongzhou Bao , Jiayi Wang , Hai Zhao

Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standardized evaluation,…

Machine Learning · Computer Science 2025-02-24 Leo Schwinn , Yan Scholten , Tom Wollschläger , Sophie Xhonneux , Stephen Casper , Stephan Günnemann , Gauthier Gidel

Contrastive learning has proven to be an effective method for pre-training models using weakly labeled data in the vision domain. Sentence transformers are the NLP counterparts to this architecture, and have been growing in popularity due…

Computation and Language · Computer Science 2023-11-30 Tanmay Chavan , Shantanu Patankar , Aditya Kane , Omkar Gokhale , Geetanjali Kale , Raviraj Joshi

Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters. Few try to attack classifiers by rewriting a whole sentence, due to the…

Computation and Language · Computer Science 2022-10-21 Lei Xu , Ivan Ramirez , Kalyan Veeramachaneni

Pre-trained models excel on NLI benchmarks like SNLI and MultiNLI, but their true language understanding remains uncertain. Models trained only on hypotheses and labels achieve high accuracy, indicating reliance on dataset biases and…

Computation and Language · Computer Science 2024-12-17 Chetan Verma , Archit Agarwal

Natural language generation (NLG) is one of the most impactful fields in NLP, and recent years have witnessed its evolution brought about by large language models (LLMs). As the key instrument for writing assistance applications, they are…

Computation and Language · Computer Science 2023-06-07 Minghui Zhang , Alex Sokolov , Weixin Cai , Si-Qing Chen

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

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that induce LLMs to generate harmful content. Current methods…

Computation and Language · Computer Science 2025-10-21 Jiawei Lian , Jianhong Pan , Lefan Wang , Yi Wang , Shaohui Mei , Lap-Pui Chau

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Machine Learning · Computer Science 2019-10-04 He Zhao , Trung Le , Paul Montague , Olivier De Vel , Tamas Abraham , Dinh Phung

Textual adversarial samples play important roles in multiple subfields of NLP research, including security, evaluation, explainability, and data augmentation. However, most work mixes all these roles, obscuring the problem definitions and…

Computation and Language · Computer Science 2022-10-20 Yangyi Chen , Hongcheng Gao , Ganqu Cui , Fanchao Qi , Longtao Huang , Zhiyuan Liu , Maosong Sun

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

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an input that result in a different model prediction. This paper…

Machine Learning · Computer Science 2020-08-05 Florian Tramèr , Jens Behrmann , Nicholas Carlini , Nicolas Papernot , Jörn-Henrik Jacobsen

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Machine Learning · Computer Science 2021-09-23 Liping Yuan , Xiaoqing Zheng , Yi Zhou , Cho-Jui Hsieh , Kai-wei Chang

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-10 Yao Qin , Nicholas Carlini , Ian Goodfellow , Garrison Cottrell , Colin Raffel

Despite promising performance on open-source large vision-language models (LVLMs), transfer-based targeted attacks often fail against closed-source commercial LVLMs. Analyzing failed adversarial perturbations reveals that the learned…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Zhaoyi Li , Xiaohan Zhao , Dong-Dong Wu , Jiacheng Cui , Zhiqiang Shen