Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead

Abstract

Machine Learning (ML) techniques have been rapidly adopted by smart Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) due to their powerful decision-making capabilities. However, they are vulnerable to various security and reliability threats, at both hardware and software levels, that compromise their accuracy. These threats get aggravated in emerging edge ML devices that have stringent constraints in terms of resources (e.g., compute, memory, power/energy), and that therefore cannot employ costly security and reliability measures. Security, reliability, and vulnerability mitigation techniques span from network security measures to hardware protection, with an increased interest towards formal verification of trained ML models. This paper summarizes the prominent vulnerabilities of modern ML systems, highlights successful defenses and mitigation techniques against these vulnerabilities, both at the cloud (i.e., during the ML training phase) and edge (i.e., during the ML inference stage), discusses the implications of a resource-constrained design on the reliability and security of the system, identifies verification methodologies to ensure correct system behavior, and describes open research challenges for building secure and reliable ML systems at both the edge and the cloud.

Final version appears in https://ieeexplore.ieee.org/document/8979377

References in corpus (8)

• Ensemble Adversarial Training: Attacks and Defenses
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Stealing Machine Learning Models via Prediction APIs
• Towards Robust Interpretability with Self-Explaining Neural Networks
• Neural Trojans
• I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators
• Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference
• TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks

Cited by in corpus (16)

• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey
• I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences
• Machine Learning on the COVID-19 Pandemic, Human Mobility and Air Quality: A Review
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
• Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
• Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks
• NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips
• Exposing Reliability Degradation and Mitigation in Approximate DNNs under Permanent Faults
• DeepVigor: Vulnerability Value Ranges and Factors for DNNs' Reliability Assessment
• Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Review
• RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks
• FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks
• Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems