Machine learning for detecting data exfiltration: A review
Context: Research at the intersection of cybersecurity, Machine Learning (ML), and Software
Engineering (SE) has recently taken significant steps in proposing countermeasures for …
Engineering (SE) has recently taken significant steps in proposing countermeasures for …
Bae: Bert-based adversarial examples for text classification
S Garg, G Ramakrishnan - arXiv preprint arXiv:2004.01970, 2020 - arxiv.org
Modern text classification models are susceptible to adversarial examples, perturbed
versions of the original text indiscernible by humans which get misclassified by the model …
versions of the original text indiscernible by humans which get misclassified by the model …
Explainable deep learning: A field guide for the uninitiated
Deep neural networks (DNNs) are an indispensable machine learning tool despite the
difficulty of diagnosing what aspects of a model's input drive its decisions. In countless real …
difficulty of diagnosing what aspects of a model's input drive its decisions. In countless real …
A closer look at accuracy vs. robustness
Current methods for training robust networks lead to a drop in test accuracy, which has led
prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning …
prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning …
[图书][B] Challenges in automated debiasing for toxic language detection
X Zhou - 2020 - search.proquest.com
Biased associations have been a challenge in the development of classifiers for detecting
toxic language, hindering both fairness and accuracy. As potential solutions, we investigate …
toxic language, hindering both fairness and accuracy. As potential solutions, we investigate …
Nl-augmenter: A framework for task-sensitive natural language augmentation
Data augmentation is an important component in the robustness evaluation of models in
natural language processing (NLP) and in enhancing the diversity of the data they are …
natural language processing (NLP) and in enhancing the diversity of the data they are …
Reevaluating adversarial examples in natural language
State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a
successful attack. We distill ideas from past work into a unified framework: a successful …
successful attack. We distill ideas from past work into a unified framework: a successful …
Evading text based emotion detection mechanism via adversarial attacks
A Bajaj, DK Vishwakarma - Neurocomputing, 2023 - Elsevier
Abstract Textual Emotion Analysis (TEA) seeks to extract and assess the emotional states of
users from the text. Various Deep Learning (DL) algorithms have emerged rapidly and …
users from the text. Various Deep Learning (DL) algorithms have emerged rapidly and …
Natural language adversarial attack and defense in word level
Up until very recently, inspired by a mass of researches on adversarial examples for
computer vision, there has been a growing interest in designing adversarial attacks for …
computer vision, there has been a growing interest in designing adversarial attacks for …
Characterizing the decision boundary of deep neural networks
Deep neural networks and in particular, deep neural classifiers have become an integral
part of many modern applications. Despite their practical success, we still have limited …
part of many modern applications. Despite their practical success, we still have limited …