Adversarial attacks and adversarial robustness in computational pathology

bioRxiv (Cold Spring Harbor Laboratory)

Abstract

Abstract Artificial Intelligence (AI) can support diagnostic workflows in oncology by aiding diagnosis and providing biomarkers. AI applications are therefore expected to evolve from academic prototypes to commercial products in the coming years. However, AI applications are vulnerable to adversarial attacks, such as malicious interference with test data aiming to cause misclassifications. Therefore, it is essential for the use of AI-based diagnostic devices to secure them against such attacks before widespread use. Unfortunately, no resistant systems exist in computational pathology so far. To address this problem, we investigate the susceptibility of convolutional neural networks (CNNs) to multiple types of white- and black-box attacks. We demonstrate that both attacks can easily confuse CNNs in clinically relevant pathology tasks and impair classification performance. Classical adversarially robust training and dual batch normalization (DBN) are possible mitigation strategies but require precise knowledge of the type of attack used in the inference. We demonstrate that vision transformers (ViTs) perform equally well compared to CNNs at baseline and are orders of magnitude more robust to different types of white-box and black-box attacks. At a mechanistic level, we show that this is associated with a more robust latent representation of clinically relevant categories in ViTs compared to CNNs. Our results are in line with previous theoretical studies. We show that ViTs are robust learners in computational pathology. This implies that large-scale rollout of AI models in computational pathology should rely on ViTs rather than CNN-based classifiers to provide inherent protection against adversaries.

Authors 11

1. Narmin Ghaffari Laleh Aachen Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

   Department of Medicine III, University Hospital RWTH Aachen

2. Daniel Truhn Aachen Department of Diagnostic and Interventional Radiology

   Universitätsklinikum Aachen

   Affiliation as printed

   Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany

   Department of Diagnostic and Interventional Radiology, University Hospital Aachen

3. Gregory Patrick Veldhuizen Aachen Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

   Department of Medicine III, University Hospital RWTH Aachen

4. Tianyu Han Aachen Department of Physics of Molecular Imaging Systems

   RWTH Aachen University

   Affiliation as printed

   Department of Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University, Aachen, Germany

   Department of Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University

5. Marko van Treeck Aachen Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

   Department of Medicine III, University Hospital RWTH Aachen

6. Roman David Buelow Aachen Institute of Pathology

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany

   Institute of Pathology, University Hospital RWTH Aachen

7. Rupert Langer

   University of Bern · Johannes Kepler University of Linz · Kepler Universitätsklinikum

   Affiliation as printed

   Institute of Pathology and Molecular Pathology, Kepler University Hospital, Johannes Kepler University Linz, Linz, Austria

   Institute of Pathology, University of Bern, Switzerland

   Institute of Pathology and Molecular Pathology, Kepler University Hospital, Johannes Kepler University Linz

   Institute of Pathology, University of Bern

8. Bastian Dislich

   University of Bern

   Affiliation as printed

   Institute of Pathology, University of Bern, Switzerland

   Institute of Pathology, University of Bern

9. Peter Boor Aachen Institute of Pathology

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany

   Institute of Pathology, University Hospital RWTH Aachen

10. Volkmar Schulz Aachen Comprehensive Diagnostic Center Aachen (CDCA) Department of Physics of Molecular Imaging Systems

    Universitätsklinikum Aachen · Fraunhofer Institute for Digital Medicine · RWTH Aachen University

    Affiliation as printed

    Comprehensive Diagnostic Center Aachen (CDCA), University Hospital Aachen, Aachen, Germany

    Department of Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University, Aachen, Germany

    Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany

    Comprehensive Diagnostic Center Aachen (CDCA), University Hospital Aachen

    Department of Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University

    Fraunhofer Institute for Digital Medicine MEVIS

11. Jakob Nikolas Kather corresponding Aachen Department of Medicine III

    University of Leeds · University Hospital Heidelberg · National Center for Tumor Diseases · Universitätsklinikum Aachen · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden · RWTH Aachen University

    Affiliation as printed

    Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

    Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany

    Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany

    Pathology & Data Analytics, Leeds Institute of Medical Research at St James’s, University of Leeds, Leeds, United Kingdom

    Department of Medicine III, University Hospital RWTH Aachen

    Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden

    Medical Oncology, National Center for Tumor Diseases (NCT), University Hospital Heidelberg

    Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds