Adversarial Examples: Opportunities and Challenges

Abstract

Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs), which are designed by attackers to fool deep learning models. Different from real examples, AEs can mislead the model to predict incorrect outputs while hardly be distinguished by human eyes, therefore threaten security-critical deep-learning applications. In recent years, the generation and defense of AEs have become a research hotspot in the field of artificial intelligence (AI) security. This article reviews the latest research progress of AEs. First, we introduce the concept, cause, characteristics and evaluation metrics of AEs, then give a survey on the state-of-the-art AE generation methods with the discussion of advantages and disadvantages. After that, we review the existing defenses and discuss their limitations. Finally, future research opportunities and challenges on AEs are prospected.

arXiv comment16 pages, 13 figures, 5 tables

References in corpus (34)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Ensemble Adversarial Training: Attacks and Defenses
• One pixel attack for fooling deep neural networks
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Delving into Transferable Adversarial Examples and Black-box Attacks
• Synthesizing Robust Adversarial Examples
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• The Space of Transferable Adversarial Examples
• Detecting Adversarial Samples from Artifacts
• On the (Statistical) Detection of Adversarial Examples
• Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• Adversarial Feature Selection against Evasion Attacks
• A study of the effect of JPG compression on adversarial images
• Defensive Distillation is Not Robust to Adversarial Examples
• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• MagNet: a Two-Pronged Defense against Adversarial Examples
• NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
• A General Framework for Adversarial Examples with Objectives
• Adversarial Patch
• Early Methods for Detecting Adversarial Images
• Adversarial Attacks Against Medical Deep Learning Systems
• Adversarial and Clean Data Are Not Twins
• Understanding and Enhancing the Transferability of Adversarial Examples
• Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
• Randomized Prediction Games for Adversarial Machine Learning
• Are Accuracy and Robustness Correlated?
• HCIC: Hardware-assisted Control-flow Integrity Checking
• The Nonlinearity Coefficient - Predicting Generalization in Deep Neural Networks
• ATMPA: Attacking Machine Learning-based Malware Visualization Detection Methods via Adversarial Examples

Cited by in corpus (29)

• Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
• Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art
• Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
• Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systems
• FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications
• On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
• Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Voting
• SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detection
• Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective
• Towards a Robust Deep Neural Network in Texts: A Survey
• There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
• CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models
• Learning Fast and Slow: PROPEDEUTICA for Real-time Malware Detection
• Adversarial Robustness via Label-Smoothing
• Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attacks
• Understanding Adversarial Robustness Through Loss Landscape Geometries
• Boosting Gradient for White-Box Adversarial Attacks
• Towards Resistant Audio Adversarial Examples
• ATMPA: Attacking Machine Learning-based Malware Visualization Detection Methods via Adversarial Examples
• Using a GAN to Generate Adversarial Examples to Facial Image Recognition
• Data-Centric Engineering: integrating simulation, machine learning and statistics. Challenges and Opportunities
• ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries
• Blind Adversarial Training: Balance Accuracy and Robustness
• Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
• PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack
• Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustness
• Enhanced countering adversarial attacks via input denoising and feature restoring
• OrcoDCS: An IoT-Edge Orchestrated Online Deep Compressed Sensing Framework
• Backdoor attacks on DNN and GBDT -- A Case Study from the insurance domain