Security and Privacy for Artificial Intelligence: Opportunities and Challenges

Abstract

The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models are vulnerable to advanced and sophisticated hacking techniques. This challenge has motivated concerted research efforts into adversarial AI, with the aim of developing robust machine and deep learning models that are resilient to different types of adversarial scenarios. In this paper, we present a holistic cyber security review that demonstrates adversarial attacks against AI applications, including aspects such as adversarial knowledge and capabilities, as well as existing methods for generating adversarial examples and existing cyber defence models. We explain mathematical AI models, especially new variants of reinforcement and federated learning, to demonstrate how attack vectors would exploit vulnerabilities of AI models. We also propose a systematic framework for demonstrating attack techniques against AI applications and reviewed several cyber defences that would protect AI applications against those attacks. We also highlight the importance of understanding the adversarial goals and their capabilities, especially the recent attacks against industry applications, to develop adaptive defences that assess to secure AI applications. Finally, we describe the main challenges and future research directions in the domain of security and privacy of AI technologies.

References in corpus (38)

• Distilling the Knowledge in a Neural Network
• Federated Learning: Strategies for Improving Communication Efficiency
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Do Deep Nets Really Need to be Deep?
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Poisoning Attacks against Support Vector Machines
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Adversarial Attacks and Defences: A Survey
• The Space of Transferable Adversarial Examples
• Security Evaluation of Pattern Classifiers under Attack
• Detecting Adversarial Samples from Artifacts
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• On the (Statistical) Detection of Adversarial Examples
• Black-box Adversarial Attacks with Limited Queries and Information
• Adversarial Perturbations Against Deep Neural Networks for Malware Classification
• CryptoDL: Deep Neural Networks over Encrypted Data
• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• Towards Crafting Text Adversarial Samples
• Generative Poisoning Attack Method Against Neural Networks
• Crypto-Nets: Neural Networks over Encrypted Data
• Stronger Data Poisoning Attacks Break Data Sanitization Defenses
• Practical Black-Box Attacks against Machine Learning
• UPSET and ANGRI : Breaking High Performance Image Classifiers
• Security Analysis of Online Centroid Anomaly Detection
• Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks
• Security and Privacy Issues in Deep Learning
• A review of homomorphic encryption and software tools for encrypted statistical machine learning
• Adversarial Examples in Modern Machine Learning: A Review
• Feature Squeezing Mitigates and Detects Carlini/Wagner Adversarial Examples
• Biometric Backdoors: A Poisoning Attack Against Unsupervised Template Updating
• Security Matters: A Survey on Adversarial Machine Learning
• Robustness to Adversarial Examples through an Ensemble of Specialists
• Query-Efficient Black-Box Attack by Active Learning