Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks
Convolutional neural networks are vulnerable to small $\ell^p$ adversarial attacks, while the human visual system is not. Inspired by neural networks in the eye and the brain, we developed a novel artificial neural network model that recurrently collects data with a log-polar field of view that is controlled by attention. We demonstrate the effectiveness of this design as a defense against SPSA and PGD adversarial attacks. It also has beneficial properties observed in the animal visual system, such as reflex-like pathways for low-latency inference, fixed amount of computation independent of image size, and rotation and scale invariance. The code for experiments is available at https://gitlab.com/exwzd-public/kiritani_ono_2020.
Code (2)
Similar Papers 제목 키워드 기반
On the Robustness of Self-Attentive Models
This work examines the robustness of self-attentive neural networks against adversarial input perturbations. Specifically, we investigate the attention and feature extraction mechanisms of state-of-the-art recurrent neur…
Machine TranslationSentiment AnalysisTranslationLow-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism
Polar codes have drawn much attention and been adopted in 5G New Radio (NR) due to their capacity-achieving performance. Recently, as the emerging deep learning (DL) technique has breakthrough achievements in many fields…
DecoderQuantizationHuman Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises
Humans actively observe the visual surroundings by focusing on salient objects and ignoring trivial details. However, computer vision models based on convolutional neural networks (CNN) often analyze visual input all at …
Adversarial RobustnessFoveationObject RecognitionFooling Polarization-based Vision using Locally Controllable Polarizing Projection
Polarization is a fundamental property of light that encodes abundant information regarding surface shape, material, illumination and viewing geometry. The computer vision community has witnessed a blossom of polarizatio…
Color ConstancyReflection RemovalSemantic SegmentationDeep-learning-based electrode action potential mapping (DEAP Mapping) from annotation-free unipolar electrogram
Catheter ablation has limited therapeutic efficacy against non-paroxysmal atrial fibrillation (AF), and electrophysiological studies using mapping catheters have been applied to evaluate the AF substrate. However, many o…