Attacking and Defending Machine Learning Applications of Public Cloud
arXiv:2008.02076
Abstract
Adversarial attack breaks the boundaries of traditional security defense. For adversarial attack and the characteristics of cloud services, we propose Security Development Lifecycle for Machine Learning applications, e.g., SDL for ML. The SDL for ML helps developers build more secure software by reducing the number and severity of vulnerabilities in ML-as-a-service, while reducing development cost.
arXiv admin note: text overlap with arXiv:1704.05051 by other authors
References in corpus (24)
- Explaining and Harnessing Adversarial Examples
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
- Countering Adversarial Images using Input Transformations
- Detecting Adversarial Samples from Artifacts
- On the (Statistical) Detection of Adversarial Examples
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
- Spatially Transformed Adversarial Examples
- Stochastic Activation Pruning for Robust Adversarial Defense
- Mitigating Adversarial Effects Through Randomization
- Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
- Practical Black-Box Attacks against Machine Learning
- Feature Denoising for Improving Adversarial Robustness
- Cascade Adversarial Machine Learning Regularized with a Unified Embedding
- Adversarial Examples for Semantic Image Segmentation
- Advbox: a toolbox to generate adversarial examples that fool neural networks
- Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examples
- Query-Efficient Black-box Adversarial Examples (superceded)
- Robust Neural Networks using Randomized Adversarial Training
- Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service
- Efficient Adversarial Training with Transferable Adversarial Examples
- An Empirical Evaluation of Adversarial Robustness under Transfer Learning
- Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield