Adversarial Attacks on Machine Learning-Aided Visualizations

Abstract

Research in ML4VIS investigates how to use machine learning (ML) techniques to generate visualizations, and the field is rapidly growing with high societal impact. However, as with any computational pipeline that employs ML processes, ML4VIS approaches are susceptible to a range of ML-specific adversarial attacks. These attacks can manipulate visualization generations, causing analysts to be tricked and their judgments to be impaired. Due to a lack of synthesis from both visualization and ML perspectives, this security aspect is largely overlooked by the current ML4VIS literature. To bridge this gap, we investigate the potential vulnerabilities of ML-aided visualizations from adversarial attacks using a holistic lens of both visualization and ML perspectives. We first identify the attack surface (i.e., attack entry points) that is unique in ML-aided visualizations. We then exemplify five different adversarial attacks. These examples highlight the range of possible attacks when considering the attack surface and multiple different adversary capabilities. Our results show that adversaries can induce various attacks, such as creating arbitrary and deceptive visualizations, by systematically identifying input attributes that are influential in ML inferences. Based on our observations of the attack surface characteristics and the attack examples, we underline the importance of comprehensive studies of security issues and defense mechanisms as a call of urgency for the ML4VIS community.

This version of the article has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/s12650-024-01029-2

References in corpus (12)

• One pixel attack for fooling deep neural networks
• The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations
• A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization
• Surfacing Visualization Mirages
• Supporting Analysis of Dimensionality Reduction Results with Contrastive Learning
• An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data
• A Deep Generative Model for Graph Layout
• Can visualization alleviate dichotomous thinking? Effects of visual representations on the cliff effect
• Table2Charts: Recommending Charts by Learning Shared Table Representations
• Selection-Bias-Corrected Visualization via Dynamic Reweighting
• Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks
• ParaDime: A Framework for Parametric Dimensionality Reduction