Adversarial Attacks and Dimensionality in Text Classifiers
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAdversarial Defensetext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Identifying Adversarial Attacks on Text Classifiers
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 AnalysisRandomized Smoothing under Attack: How Good is it in Pratice?
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
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…
SentenceEvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attacks
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 AttackOn The Robustness of Offensive Language Classifiers
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,…