Wu-chi Feng

Li-Yun Wang, Yeganeh Jalalpour, Wu-chi Feng

This paper presents a novel context-aware image denoising algorithm that combines an adaptive image smoothing technique and color reduction techniques to remove perturbation from adversarial images. Adaptive image smoothing is achieved using auto-threshold canny edge detection to produce an accurate edge map used to produce a blurred image that preserves more edge features. The proposed algorithm then uses color reduction techniques to reconstruct the image using only a few representative colors. Through this technique, the algorithm can reduce the effects of adversarial perturbations on images. We also discuss experimental data on classification accuracy. Our results showed that the proposed approach reduces adversarial perturbation in adversarial attacks and increases the robustness of the deep convolutional neural network models.

Ryan Feng, Wu-chi Feng, Atul Prakash

Preprocessing defenses such as pixel discretization are appealing to remove adversarial attacks due to their simplicity. However, they have been shown to be ineffective except on simple datasets like MNIST. We hypothesize that existing discretization approaches failed because using a fixed codebook for the entire dataset limits their ability to balance image representation and codeword separability. We first formally prove that adaptive codebooks can provide stronger robustness guarantees than fixed codebooks as a preprocessing defense on some datasets. Based on that insight, we propose a content-adaptive pixel discretization defense called Essential Features, which discretizes the image to a per-image adaptive codebook to reduce the color space. We then find that Essential Features can be further optimized by applying adaptive blurring before the discretization to push perturbed pixel values back to their original value before determining the codebook. Against adaptive attacks, we show that content-adaptive pixel discretization extends the range of datasets that benefit in terms of both L_2 and L_infinity robustness where previously fixed codebooks were found to have failed. Our findings suggest that content-adaptive pixel discretization should be part of the repertoire for making models robust.