SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters
In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image. We validate our technique on Convolutional DNNs against the state-of-the-art attacks from the open-source Cleverhans library using the MNIST, the CIFAR-10, and the CIFAR-100 datasets. Our experimental results show that the attack success rate, as well as the imperceptibility of the adversarial images, can be significantly reduced by adding effective pre-processing functions, i.e., Sobel filtering.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improving Adversarial Robustness via Channel-wise Activation Suppressing
The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing works, in this paper, we highlight two n…
Adversarial RobustnessRoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training
Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. S…
Adversarial RobustnessCrypTFlow2: Practical 2-Party Secure Inference
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both correct -- i.e., their outputs are bitwise …
QUOTIENT: Two-Party Secure Neural Network Training and Prediction
Recently, there has been a wealth of effort devoted to the design of secure protocols for machine learning tasks. Much of this is aimed at enabling secure prediction from highly-accurate Deep Neural Networks (DNNs). Howe…
PredictionVocal Bursts Valence PredictionSlalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environ…
GPU