DeepAI
Log In Sign Up

The Sensitivity of Word Embeddings-based Author Detection Models to Semantic-preserving Adversarial Perturbations

02/23/2021
by   Jeremiah Duncan, et al.
0

Authorship analysis is an important subject in the field of natural language processing. It allows the detection of the most likely writer of articles, news, books, or messages. This technique has multiple uses in tasks related to authorship attribution, detection of plagiarism, style analysis, sources of misinformation, etc. The focus of this paper is to explore the limitations and sensitiveness of established approaches to adversarial manipulations of inputs. To this end, and using those established techniques, we first developed an experimental frame-work for author detection and input perturbations. Next, we experimentally evaluated the performance of the authorship detection model to a collection of semantic-preserving adversarial perturbations of input narratives. Finally, we compare and analyze the effects of different perturbation strategies, input and model configurations, and the effects of these on the author detection model.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/04/2020

Can Adversarial Weight Perturbations Inject Neural Backdoors?

Adversarial machine learning has exposed several security hazards of neu...
12/29/2021

Repairing Adversarial Texts through Perturbation

It is known that neural networks are subject to attacks through adversar...
04/06/2021

Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models

Although end-to-end automatic speech recognition (e2e ASR) models are wi...
03/15/2019

On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models

Adversarial examples --- perturbations to the input of a model that elic...
09/27/2019

Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest

In this paper we investigate the usage of adversarial perturbations for ...
10/18/2019

Understanding Deep Networks via Extremal Perturbations and Smooth Masks

The problem of attribution is concerned with identifying the parts of an...
07/02/2018

Adversarial Perturbations Against Real-Time Video Classification Systems

Recent research has demonstrated the brittleness of machine learning sys...