Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety

Abstract

The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability to problems with malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from safety concerns. In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged. This work provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern ML methods. We moreover hope that our contribution fuels discussions on desiderata for ML systems and strategies on how to propel existing approaches accordingly.

94 pages

References in corpus (55)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Explaining and Harnessing Adversarial Examples
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Semantic Segmentation
• Striving for Simplicity: The All Convolutional Net
• On Calibration of Modern Neural Networks
• Weight Uncertainty in Neural Networks
• Compressing Deep Convolutional Networks using Vector Quantization
• SmoothGrad: removing noise by adding noise
• Random Erasing Data Augmentation
• The Loss Surfaces of Multilayer Networks
• Deep Bayesian Active Learning with Image Data
• Domain Generalization via Invariant Feature Representation
• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• Domain Generalization via Model-Agnostic Learning of Semantic Features
• Deep Anomaly Detection with Outlier Exposure
• Regularizing Neural Networks by Penalizing Confident Output Distributions
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Deep Gaussian Processes
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• Fully Connected Deep Structured Networks
• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
• Robust PCA via Outlier Pursuit
• Regularization for Deep Learning: A Taxonomy
• Simple Black-Box Adversarial Perturbations for Deep Networks
• Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
• On Physical Adversarial Patches for Object Detection
• Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
• Learning Robust Representations by Projecting Superficial Statistics Out
• UPSET and ANGRI : Breaking High Performance Image Classifiers
• Rule Extraction Algorithm for Deep Neural Networks: A Review
• Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning
• Frustratingly Simple Domain Generalization via Image Stylization
• STFCN: Spatio-Temporal FCN for Semantic Video Segmentation
• Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
• Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
• DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
• Hyp-RL : Hyperparameter Optimization by Reinforcement Learning
• Robust PCA in High-dimension: A Deterministic Approach
• Towards Unified INT8 Training for Convolutional Neural Network
• Confidence Calibration for Object Detection and Segmentation
• Complement Objective Training
• Transferable Universal Adversarial Perturbations Using Generative Models
• Strategy to Increase the Safety of a DNN-based Perception for HAD Systems
• Disentangled Representation Learning with Wasserstein Total Correlation
• Supervised Dimensionality Reduction and Visualization using Centroid-encoder
• Efficacy of Pixel-Level OOD Detection for Semantic Segmentation
• Learning Robust Low-Rank Representations
• L 1-norm double backpropagation adversarial defense
• A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs
• Learning Implicit Generative Models Using Differentiable Graph Tests
• Outlier Detection and Data Clustering via Innovation Search

Cited by in corpus (7)

• A Review of Product Safety Regulations in the European Union
• Yes We Care! -- Certification for Machine Learning Methods through the Care Label Framework
• SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving
• Conditioning Latent-Space Clusters for Real-World Anomaly Classification
• Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces
• The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning
• Detecting underdetermination in parameterized quantum circuits