Extractive adversarial networks: High-recall explanations for identifying personal attacks in social media posts
We introduce an adversarial method for producing high-recall explanations of neural text
classifier decisions. Building on an existing architecture for extractive explanations via hard …
classifier decisions. Building on an existing architecture for extractive explanations via hard …
Additive feature attribution explainable methods to craft adversarial attacks for text classification and text regression
Deep learning (DL) models have significantly improved the performance of text classification
and text regression tasks. However, DL models are often strikingly vulnerable to adversarial …
and text regression tasks. However, DL models are often strikingly vulnerable to adversarial …
CATBERT: Context-aware tiny BERT for detecting social engineering emails
Targeted phishing emails are on the rise and facilitate the theft of billions of dollars from
organizations a year. While malicious signals from attached files or malicious URLs in …
organizations a year. While malicious signals from attached files or malicious URLs in …
Adversarial attacks and defenses for social network text processing applications: Techniques, challenges and future research directions
The growing use of social media has led to the development of several Machine Learning
(ML) and Natural Language Processing (NLP) tools to process the unprecedented amount …
(ML) and Natural Language Processing (NLP) tools to process the unprecedented amount …
Data-driven mitigation of adversarial text perturbation
Social networks have become an indispensable part of our lives, with billions of people
producing ever-increasing amounts of text. At such scales, content policies and their …
producing ever-increasing amounts of text. At such scales, content policies and their …
Adversarial text generation for google's perspective api
E Jain, S Brown, J Chen, E Neaton… - 2018 international …, 2018 - ieeexplore.ieee.org
With the preponderance of harassment and abuse, social media platforms and online
discussion platforms seek to curb toxic comments. Google's Perspective aims to help …
discussion platforms seek to curb toxic comments. Google's Perspective aims to help …
Generating natural language adversarial examples on a large scale with generative models
Today text classification models have been widely used. However, these classifiers are
found to be easily fooled by adversarial examples. Fortunately, standard attacking methods …
found to be easily fooled by adversarial examples. Fortunately, standard attacking methods …
Generating black-box adversarial examples for text classifiers using a deep reinforced model
P Vijayaraghavan, D Roy - … 2019, Würzburg, Germany, September 16–20 …, 2020 - Springer
Recently, generating adversarial examples has become an important means of measuring
robustness of a deep learning model. Adversarial examples help us identify the …
robustness of a deep learning model. Adversarial examples help us identify the …
Learning to discriminate perturbations for blocking adversarial attacks in text classification
Adversarial attacks against machine learning models have threatened various real-world
applications such as spam filtering and sentiment analysis. In this paper, we propose a …
applications such as spam filtering and sentiment analysis. In this paper, we propose a …
Robust training under linguistic adversity
Deep neural networks have achieved remarkable results across many language processing
tasks, however they have been shown to be susceptible to overfitting and highly sensitive to …
tasks, however they have been shown to be susceptible to overfitting and highly sensitive to …