paper-with-me

Papers

Adversarial Attacks and Dimensionality in Text Classifiers

2024-04-03 · Nandish Chattopadhyay, Atreya Goswami, Anupam Chattopadhyay

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications. These attacks introduce minute and structured perturbations or alterations in the test samples, imperceptible to human annotators in general, but trained neural networks and other models are sensitive to it. Historically, adversarial attacks have been first identified and studied in the domain of image processing. In this paper, we study adversarial examples in the field of natural language processing, specifically text classification tasks. We investigate the reasons for adversarial vulnerability, particularly in relation to the inherent dimensionality of the model. Our key finding is that there is a very strong correlation between the embedding dimensionality of the adversarial samples and their effectiveness on models tuned with input samples with same embedding dimension. We utilize this sensitivity to design an adversarial defense mechanism. We use ensemble models of varying inherent dimensionality to thwart the attacks. This is tested on multiple datasets for its efficacy in providing robustness. We also study the problem of measuring adversarial perturbation using different distance metrics. For all of the aforementioned studies, we have run tests on multiple models with varying dimensionality and used a word-vector level adversarial attack to substantiate the findings.

📄 PDF Abstract BibTeX arXiv:2404.02660

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial Defensetext-classificationText Classification

Similar Papers 제목 키워드 기반

Identifying Adversarial Attacks on Text Classifiers

2022-01-21 · Zhouhang Xie, Jonathan Brophy, Adam Noack, Wencong You 외

The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, ther…

Abuse DetectionAdversarial TextLanguage ModellingSentiment Analysis

Randomized Smoothing under Attack: How Good is it in Pratice?

2022-04-28 · Thibault Maho, Teddy Furon, Erwan Le Merrer

Randomized smoothing is a recent and celebrated solution to certify the robustness of any classifier. While it indeed provides a theoretical robustness against adversarial attacks, the dimensionality of current classifie…

Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations

2022-04-29 · RepL4NLP (ACL) 2022 5 · Na Liu, Mark Dras, Wei Emma Zhang

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, succe…

Sentence

EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attacks

2021-07-12 · Andrei Ilie, Marius Popescu, Alin Stefanescu

Recent work has shown how easily white-box adversarial attacks can be applied to state-of-the-art image classifiers. However, real-life scenarios resemble more the black-box adversarial conditions, lacking transparency a…

Adversarial Attack

On The Robustness of Offensive Language Classifiers

2022-03-21 · ACL 2022 5 · Jonathan Rusert, Zubair Shafiq, Padmini Srinivasan

Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale. However, despite their real-world deployment,…