Trustworthy AI: From Principles to Practices

Abstract

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection. These shortcomings degrade user experience and erode people’s trust in all AI systems. In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability. To unify currently available but fragmented approaches toward trustworthy AI, we organize them in a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to system development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items for practitioners and societal stakeholders (e.g., researchers, engineers, and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges for the future development of trustworthy AI systems, where we identify the need for a paradigm shift toward comprehensively trustworthy AI systems.

Identity of AI

“…Privacy, manipulation, opacity, bias, human-robot interaction, employment, the effects of autonomy, machine ethics, artificial moral agency, and AI superintelligence (AGI) [93]; Proportionality and do no harm, safety and security, fairness and non-discrimination, sustainability, right to privacy and data protection, human oversight and determination, transparency and explainability, responsibility and accountability, awareness and literacy, and multi-stakeholder and adaptive governance and collaboration [94] Responsible AI A set of principled and actionable norms to ensure organizations develop and deploy AI responsibly Accountability, transparency, fairness, reliability and safety, privacy and security, and inclusiveness [95] Trustworthy AI Ethically sound, technically robust, resilient, and lawful AI, built with trust throughout its lifecycle Robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability [96]; Beneficence, non-maleficence, autonomy, justice, and explicability [97]; Reliability, safety, security, privacy, availability, usability, accuracy, robustness, fairness, accountability, transparency, interpretability/explainability, ethical data collection and use of the system outcome, and more (yet to be defined) [98] Sustainable AI AI developed and deployed in a way compatible with sustaining environmental resources, economic models and societal values Environmental protection, reduced carbon footprints, reduced energy consumption, protecting people, legal frameworks [75] Vol:. (1234567890)…”

Comparative Analyses of Unsupervised PCA K-Means Change Detection Algorithm from the Viewpoint of Follow-Up Plan

“…In addition, classical methods generally provide more transparency, explainability, and interpretability than more complex ones do [ 14 ]. These properties support the system’s trustworthiness [ 15 , 16 , 17 ], which is significant for any response to the detected change.…”

ImDrug: A Benchmark for Deep Imbalanced Learning in AI-aided Drug Discovery

“…Despite the success of deep learning in AIDD, by examining a myriad of medicinal chemistry databases and benchmarks [6,10,11,[18][19][20][21], we observe that these curated data repositories ubiquitously exhibit imbalanced distributions regardless of the specific tasks and domains 2 . This observation is reminiscent of the power-law scaling in networks [22] and the Pareto principle [23], which poses significant challenges for developing unbiased and generalizable AI algorithms [24].…”