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.
The Many Faces of Adversarial Machine Learning
Adversarial machine learning (AML) research is concerned with robustness of machine learning models and algorithms to malicious tampering. Originating at the intersection between machine learning and cybersecurity, AML has come to have broader research appeal, stretching traditional notions of security to include applications of computer vision, natural language processing, and network science. In addition, the problems of strategic classification, algorithmic recourse, and counterfactual explanations have essentially the same core mathematical structure as AML, despite distinct motivations. I give a simplified overview of the central problems in AML, and then discuss both the security-motivated AML domains, and the problems above unrelated to security. These together span a number of important AI subdisciplines, but can all broadly be viewed as concerned with trustworthy AI. My goal is to clarify both the technical connections among these, as
well as the substantive differences, suggesting directions for future research.
more »
« less
- NSF-PAR ID:
- 10383416
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- ISSN:
- 2159-5399
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
Artificial Intelligence (AI) bots receive much attention and usage in industry manufacturing and even store cashier applications. Our research is to train AI bots to be software engineering assistants, specifically to detect biases and errors inside AI software applications. An example application is an AI machine learning system that sorts and classifies people according to various attributes, such as the algorithms involved in criminal sentencing, hiring, and admission practices. Biases, unfair decisions, and flaws in terms of the equity, diversity, and justice presence, in such systems could have severe consequences. As a Hispanic-Serving Institution, we are concerned about underrepresented groups and devoted an extended amount of our time to implementing “An Assure AI” (AAAI) Bot to detect biases and errors in AI applications. Our state-of-the-art AI Bot was developed based on our previous accumulated research in AI and Deep Learning (DL). The key differentiator is that we are taking a unique approach: instead of cleaning the input data, filtering it out and minimizing its biases, we trained our deep Neural Networks (NN) to detect and mitigate biases of existing AI models. The backend of our bot uses the Detection Transformer (DETR) framework, developed by Facebook,more » « less
-
Fostering public AI literacy has been a growing area of interest at CHI for several years, and a substantial community is forming around issues such as teaching children how to build and program AI systems, designing learning experiences to broaden public understanding of AI, developing explainable AI systems, understanding how novices make sense of AI, and exploring the relationship between public policy, ethics, and AI literacy. Previous workshops related to AI literacy have been held at other conferences (e.g., SIGCSE, AAAI) that have been mostly focused on bringing together researchers and educators interested in AI education in K-12 classroom environments, an important subfield of this area. Our workshop seeks to cast a wider net that encompasses both HCI research related to introducing AI in K-12 education and also HCI research that is concerned with issues of AI literacy more broadly, including adult education, interactions with AI in the workplace, understanding how users make sense of and learn about AI systems, research on developing explainable AI (XAI) for non-expert users, and public policy issues related to AI literacy.more » « less
-
null (Ed.)Abstract Machine learning and artificial intelligence (ML/AI) methods have been used successfully in recent years to solve problems in many areas, including image recognition, unsupervised and supervised classification, game-playing, system identification and prediction, and autonomous vehicle control. Data-driven machine learning methods have also been applied to fusion energy research for over 2 decades, including significant advances in the areas of disruption prediction, surrogate model generation, and experimental planning. The advent of powerful and dedicated computers specialized for large-scale parallel computation, as well as advances in statistical inference algorithms, have greatly enhanced the capabilities of these computational approaches to extract scientific knowledge and bridge gaps between theoretical models and practical implementations. Large-scale commercial success of various ML/AI applications in recent years, including robotics, industrial processes, online image recognition, financial system prediction, and autonomous vehicles, have further demonstrated the potential for data-driven methods to produce dramatic transformations in many fields. These advances, along with the urgency of need to bridge key gaps in knowledge for design and operation of reactors such as ITER, have driven planned expansion of efforts in ML/AI within the US government and around the world. The Department of Energy (DOE) Office of Science programs in Fusion Energy Sciences (FES) and Advanced Scientific Computing Research (ASCR) have organized several activities to identify best strategies and approaches for applying ML/AI methods to fusion energy research. This paper describes the results of a joint FES/ASCR DOE-sponsored Research Needs Workshop on Advancing Fusion with Machine Learning, held April 30–May 2, 2019, in Gaithersburg, MD (full report available at https://science.osti.gov/-/media/fes/pdf/workshop-reports/FES_ASCR_Machine_Learning_Report.pdf ). The workshop drew on broad representation from both FES and ASCR scientific communities, and identified seven Priority Research Opportunities (PRO’s) with high potential for advancing fusion energy. In addition to the PRO topics themselves, the workshop identified research guidelines to maximize the effectiveness of ML/AI methods in fusion energy science, which include focusing on uncertainty quantification, methods for quantifying regions of validity of models and algorithms, and applying highly integrated teams of ML/AI mathematicians, computer scientists, and fusion energy scientists with domain expertise in the relevant areas.more » « less
-
Contribution: A novel proactive and collaborative learning paradigm was proposed to engage learners with different backgrounds and enable effective retention and transfer of the multidisciplinary artificial intelligence (AI)-cybersecurity knowledge. Specifically, the proposed learning paradigm contains: 1) an immersive learning environment to motivate the students for exploring AI/machine learning (ML) development in the context of real-world cybersecurity scenarios by constructing learning models with tangible objects and 2) a proactive education paradigm designed with the use of collaborative learning activities based on game-based learning and social constructivism. Background: Increasing evidence shows that AI techniques can be manipulated, evaded, and misled, which can result in new and profound security implications. There is an education and training gap to foster a qualified cyber-workforce that understands the usefulness, limitations, and best practices of AI technologies in the cybersecurity domain. Efforts have been made to incorporate a comprehensive curriculum to meet the demand. There still remain essential challenges for effectively educating students on the interaction of AI and cybersecurity. Intended Outcomes: A novel proactive and collaborative learning paradigm is proposed to educate and train a qualified cyber-workforce in this new era where security breaches, privacy violations, and AI have become commonplace. Application Design: The development of this learning paradigm is grounded in the pedagogical approaches of technology-mediated learning and social constructivism. Findings: Although the research work is still ongoing, the prototype learning paradigm has shown encouraging results in promoting the learners’ engagement in applied AI learning.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
