Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • Article
  • Proceedings of the International Joint Conference on Artificial Intelligence

Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error

By: Celia Cintas, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan and Edward McFowland III
  • Format:Print
ShareBar

Abstract

Reliably detecting attacks in a given set of inputs is of high practical relevance because of the vulnerability of neural networks to adversarial examples. These altered inputs create a security risk in applications with real-world consequences, such as self-driving cars, robotics and financial services. We propose an unsupervised method for detecting adversarial attacks in inner layers of autoencoder (AE) networks by maximizing a non-parametric measure of anomalous node activations. Previous work in this space has shown AE networks can detect anomalous images by thresholding the reconstruction error produced by the final layer. Furthermore, other detection methods rely on data augmentation or specialized training techniques which must be asserted before training time. In contrast, we use subset scanning methods from the anomalous pattern detection domain to enhance detection power without labeled examples of the noise, retraining or data augmentation methods. In addition to an anomalous “score” our proposed method also returns the subset of nodes within the AE network that contributed to that score. This will allow future work to pivot from detection to visualisation and explainability. Our scanning approach shows consistently higher detection power than existing detection methods across several adversarial noise models and a wide range of perturbation strengths.

Keywords

Autoencoder Networks; Pattern Detection; Subset Scanning; Computer Vision; Statistical Methods And Machine Learning; Machine Learning; Deep Learning; Data Mining; Big Data; Large-scale Systems; Mathematical Methods; Analytics and Data Science

Citation

Cintas, Celia, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan, and Edward McFowland III. "Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error." Proceedings of the International Joint Conference on Artificial Intelligence 29th (2020).
  • Read Now

About The Author

Edward McFowland III

Technology and Operations Management
→More Publications

More from the Authors

    • March 2025
    • Information and Organization

    Novice Risk Work: How Juniors Coaching Seniors on Emerging Technologies Such as Generative AI Can Lead to Learning Failures

    By: Katherine C. Kellogg, Hila Lifshitz-Assaf, Steven Randazzo, Ethan Mollick, Fabrizio Dell'Acqua, Edward McFowland III, François Candelon and Karim R. Lakhani
    • May 2024
    • Faculty Research

    Pernod Ricard: Uncorking Digital Transformation

    By: Iavor Bojinov, Edward McFowland III, François Candelon, Nikolina Jonsson and Emer Moloney
    • January 2024
    • Bioinformatics

    Subset Scanning for Multi-Trait Analysis Using GWAS Summary Statistics

    By: Rui Cao, Evan Olawsky, Edward McFowland III, Erin Marcotte, Logan Spector and Tianzhong Yang
More from the Authors
  • Novice Risk Work: How Juniors Coaching Seniors on Emerging Technologies Such as Generative AI Can Lead to Learning Failures By: Katherine C. Kellogg, Hila Lifshitz-Assaf, Steven Randazzo, Ethan Mollick, Fabrizio Dell'Acqua, Edward McFowland III, François Candelon and Karim R. Lakhani
  • Pernod Ricard: Uncorking Digital Transformation By: Iavor Bojinov, Edward McFowland III, François Candelon, Nikolina Jonsson and Emer Moloney
  • Subset Scanning for Multi-Trait Analysis Using GWAS Summary Statistics By: Rui Cao, Evan Olawsky, Edward McFowland III, Erin Marcotte, Logan Spector and Tianzhong Yang
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College.