Multi-head Uncertainty Inference for Adversarial Attack Detection
Deep neural networks (DNNs) are sensitive and susceptible to tiny perturbation by adversarial attacks which causes erroneous predictions. Various methods, including adversarial defense and uncertainty inference (UI), have been developed in recent years to overcome the adversarial attacks. In this pa...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Deep neural networks (DNNs) are sensitive and susceptible to tiny
perturbation by adversarial attacks which causes erroneous predictions. Various
methods, including adversarial defense and uncertainty inference (UI), have
been developed in recent years to overcome the adversarial attacks. In this
paper, we propose a multi-head uncertainty inference (MH-UI) framework for
detecting adversarial attack examples. We adopt a multi-head architecture with
multiple prediction heads (i.e., classifiers) to obtain predictions from
different depths in the DNNs and introduce shallow information for the UI.
Using independent heads at different depths, the normalized predictions are
assumed to follow the same Dirichlet distribution, and we estimate distribution
parameter of it by moment matching. Cognitive uncertainty brought by the
adversarial attacks will be reflected and amplified on the distribution.
Experimental results show that the proposed MH-UI framework can outperform all
the referred UI methods in the adversarial attack detection task with different
settings. |
---|---|
DOI: | 10.48550/arxiv.2212.10006 |