skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Friday, September 13 until 2:00 AM ET on Saturday, September 14 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the NSF-PAR

This content will become publicly available on February 7, 2025

Title: Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance

Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact. However, recent studies have identified new attack surfaces and risks caused by security, privacy, and fairness issues in AI systems. In this paper, we review representative techniques, algorithms, and theoretical foundations for trustworthy distributed AI through robustness guarantee, privacy protection, and fairness awareness in distributed learning. We first provide a brief overview of alternative architectures for distributed learning, discuss inherent vulnerabilities for security, privacy, and fairness of AI algorithms in distributed learning, and analyze why these problems are present in distributed learning regardless of specific architectures. Then we provide a unique taxonomy of countermeasures for trustworthy distributed AI, covering (1) robustness to evasion attacks and irregular queries at inference, and robustness to poisoning attacks, Byzantine attacks, and irregular data distribution during training; (2) privacy protection during distributed learning and model inference at deployment; and (3) AI fairness and governance with respect to both data and models. We conclude with a discussion on open challenges and future research directions toward trustworthy distributed AI, such as the need for trustworthy AI policy guidelines, the AI responsibility-utility co-design, and incentives and compliance.

  more » « less
Award ID(s):
2312758
NSF-PAR ID:
10515962
Author(s) / Creator(s):
;
Publisher / Repository:
ACM
Date Published:
Journal Name:
ACM Computing Surveys
ISSN:
0360-0300
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , 35th Annual Computer Security Applications Conference (ACSAC))
    null (Ed.)
    The prevalence of deep learning has drawn attention to the privacy protection of sensitive data. Various privacy threats have been presented, where an adversary can steal model owners' private data. Meanwhile, countermeasures have also been introduced to achieve privacy-preserving deep learning. However, most studies only focused on data privacy during training, and ignored privacy during inference. In this paper, we devise a new set of attacks to compromise the inference data privacy in collaborative deep learning systems. Specifically, when a deep neural network and the corresponding inference task are split and distributed to different participants, one malicious participant can accurately recover an arbitrary input fed into this system, even if he has no access to other participants' data or computations, or to prediction APIs to query this system. We evaluate our attacks under different settings, models and datasets, to show their effectiveness and generalization. We also study the characteristics of deep learning models that make them susceptible to such inference privacy threats. This provides insights and guidelines to develop more privacy-preserving collaborative systems and algorithms. 
    more » « less
  2. ; ; ; ; ; ( , 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC))
    This survey paper provides an overview of the current state of Artificial Intelligence (AI) attacks and risks for AI security and privacy as artificial intelligence becomes more prevalent in various applications and services. The risks associated with AI attacks and security breaches are becoming increasingly apparent and cause many financial and social losses. This paper will categorize the different types of attacks on AI models, including adversarial attacks, model inversion attacks, poisoning attacks, data poisoning attacks, data extraction attacks, and membership inference attacks. The paper also emphasizes the importance of developing secure and robust AI models to ensure the privacy and security of sensitive data. Through a systematic literature review, this survey paper comprehensively analyzes the current state of AI attacks and risks for AI security and privacy and detection techniques. 
    more » « less
  3. ( , Proc. of the 17th IEEE International Workshop on Security, Trust, and Privacy for Software Applications)
    This survey paper provides an overview of the current state of Artificial Intelligence (AI) attacks and risks for AI security and privacy as artificial intelligence becomes more prevalent in various applications and services. The risks associated with AI attacks and security breaches are becoming increasingly apparent and cause many financial and social losses. This paper will categorize the different types of attacks on AI models, including adversarial attacks, model inversion attacks, poisoning attacks, data poisoning attacks, data extraction attacks, and membership inference attacks. The paper also emphasizes the importance of developing secure and robust AI models to ensure the privacy and security of sensitive data. Through a systematic literature review, this survey paper comprehensively analyzes the current state of AI attacks and risks for AI security and privacy and detection techniques. 
    more » « less
  4. ; ; ( , 2023 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT))
    Machine Learning (ML) algorithms have shown quite promising applications in smart meter data analytics enabling intelligent energy management systems for the Advanced Metering Infrastructure (AMI). One of the major challenges in developing ML applications for the AMI is to preserve user privacy while allowing active end-users participation. This paper addresses this challenge and proposes Differential Privacy-enabled AMI with Federated Learning (DP-AMI-FL), framework for ML-based applications in the AMI. This framework provides two layers of privacy protection: first, it keeps the raw data of consumers hosting ML applications at edge devices (smart meters) with Federated Learning (FL), and second, it obfuscates the ML models using Differential Privacy (DP) to avoid privacy leakage threats on the models posed by various inference attacks. The framework is evaluated by analyzing its performance on a use case aimed to improve Short-Term Load Forecasting (STLF) for residential consumers having smart meters and home energy management systems. Extensive experiments demonstrate that the framework when used with Long Short-Term Memory (LSTM) recurrent neural network models, achieves high forecasting accuracy while preserving users data privacy. 
    more » « less
  5. ; ; ; ; ; ( , ACM Computing Surveys)
    Cloud computing is a network model of on-demand access for sharing configurable computing resource pools. Compared with conventional service architectures, cloud computing introduces new security challenges in secure service management and control, privacy protection, data integrity protection in distributed databases, data backup, and synchronization. Blockchain can be leveraged to address these challenges, partly due to the underlying characteristics such as transparency, traceability, decentralization, security, immutability, and automation. We present a comprehensive survey of how blockchain is applied to provide security services in the cloud computing model and we analyze the research trends of blockchain-related techniques in current cloud computing models. During the reviewing, we also briefly investigate how cloud computing can affect blockchain, especially about the performance improvements that cloud computing can provide for the blockchain. Our contributions include the following: (i) summarizing the possible architectures and models of the integration of blockchain and cloud computing and the roles of cloud computing in blockchain; (ii) classifying and discussing recent, relevant works based on different blockchain-based security services in the cloud computing model; (iii) simply investigating what improvements cloud computing can provide for the blockchain; (iv) introducing the current development status of the industry/major cloud providers in the direction of combining cloud and blockchain; (v) analyzing the main barriers and challenges of integrated blockchain and cloud computing systems; and (vi) providing recommendations for future research and improvement on the integration of blockchain and cloud systems. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email