Sun. Sep 25th, 2022
    en flag
    nl flag
    et flag
    fi flag
    fr flag
    de flag
    pt flag
    ru flag
    es flag

    Content Assessment: NIST Proposes Four Principles for Explainable AI Systems

    Information - 95%
    Insight - 95%
    Relevance - 90%
    Objectivity - 100%
    Authority - 100%



    A short percentage-based assessment of the qualitative benefit of the recent post sharing NIST's proposed principles for explainable artificial intelligence.

    Editor’s Note: As shared in a August 18, 2020, news release from NIST, NIST electronic engineer Jonathon Phillips notes that, “AI is becoming involved in high-stakes decisions, and no one wants machines to make them without an understanding of why. But an explanation that would satisfy an engineer might not work for someone with a different background.” It is this desire for satisfactory explanations that has resulted in the draft publication, Four Principles of Explainable Artificial Intelligence (Draft NISTIR 8312). An extract from this draft publication currently open for public comment and a copy of the publication are provided for your consideration.

    Four Principles of Explainable Artificial Intelligence*

    Authored by P. Jonathon Phillips, Carina A. Hahn, Peter C. Fontana, David Broniatowski, and Mark A. Przybocki


    With recent advances in artificial intelligence (AI), AI systems have become components of high-stakes decision processes. The nature of these decisions has spurred a drive to create algorithms, methods, and techniques to accompany outputs from AI systems with explanations. This drive is motivated in part by laws and regulations which state that decisions, including those from automated systems, provide information about the logic behind those decisions and the desire to create trustworthy AI.

    Based on these calls for explainable systems, it can be assumed that the failure to articulate the rationale for an answer can affect the level of trust users will grant that system. Suspicions that the system is biased or unfair can raise concerns about harm to oneself and to society. This may slow societal acceptance and adoption of the technology, as members of the general public oftentimes place the burden of meeting societal goals on manufacturers and programmers themselves. Therefore, in terms of societal acceptance and trust, developers of AI systems may need to consider that multiple attributes of an AI system can influence public perception of the system.

    Explainable AI is one of several properties that characterize trust in AI systems. Other properties include resiliency, reliability, bias, and accountability. Usually, these terms are not defined in isolation, but as a part or a set of principles or pillars. The definitions vary by author, and they focus on the norms that society expects AI systems to follow. For this paper, we state four principles encompassing the core concepts of explainable AI. These are informed by research from the fields of computer science, engineering, and psychology. In considering aspects across these fields, this report provides a set of contributions. First, we articulate the four principles of explainable AI. From a computer science perspective, we place existing explainable AI algorithms and systems into the context of these four principles. From a psychological perspective, we investigate how well people’s explanations follow our four principles. This provides a baseline comparison for progress in explainable AI.

    Although these principles may affect the methods in which algorithms operate to meet explainable AI goals, the focus of the concepts is not algorithmic methods or computations themselves. Rather, we outline a set of principles that organize and review existing work in explainable AI and guide future research directions for the field. These principles support the foundation of policy considerations, safety, acceptance by society, and other aspects of AI technology.

    Four Principles of Explainable AI

    We present four fundamental principles for explainable AI systems. These principles are heavily influenced by considering the AI system’s interaction with the human recipient of the information. The requirements of the given situation, the task at hand, and the consumer The Fair Credit Reporting Act (FCRA) and the European Union (E.U.) General Data Protection Regulation (GDPR) Article 13. will all influence the type of explanation deemed appropriate for the situation. These situations can include, but are not limited to, regulator and legal requirements, quality control of an AI system, and customer relations. Our four principles are intended to capture a broad set of motivations, reasons, and perspectives.

    Before proceeding with the principles, we need to define a key term, the output of an AI system. The output is the result of a query to an AI system. The output of a system varies by task. A loan application is an example where the output is a decision: approved or denied. For a recommendation system, the output could be a list of recommended movies. For a grammar checking system, the output is grammatical errors and recommended corrections.

    Briefly, our four principles of explainable AI are:

    • Explanation:  Systems deliver accompanying evidence or reason(s) for all outputs.
    • Meaningful:  Systems provide explanations that are understandable to individual users.
    • Explanation Accuracy: The explanation correctly reflects the system’s process for generating the output.
    • Knowledge Limits: The system only operates under conditions for which it was designed or when the system reaches a sufficient confidence in its output.

    Read the Complete Draft Publication on Explainable Artificial Intelligence (PDF)

    NIST Explainable AI Draft – August 2020

    Read more on Explainable Artificial Intelligence

    Additional Reading

    Source: ComplexDiscovery

    * Published with permission.


    Have a Request?

    If you have information or offering requests that you would like to ask us about, please let us know and we will make our response to you a priority.

    ComplexDiscovery is an online publication that highlights cyber, data, and legal discovery insight and intelligence ranging from original research to aggregated news for use by cybersecurity, information governance, and eDiscovery professionals. The highly targeted publication seeks to increase the collective understanding of readers regarding cyber, data, and legal discovery information and issues and to provide an objective resource for considering trends, technologies, and services related to electronically stored information.

    ComplexDiscovery OÜ is a technology marketing firm providing strategic planning and tactical execution expertise in support of cyber, data, and legal discovery organizations. Focused primarily on supporting the ComplexDiscovery publication, the company is registered as a private limited company in the European Union country of Estonia, one of the most digitally advanced countries in the world. The company operates virtually worldwide to deliver marketing consulting and services.

    Leaning Forward? The CISA 2023-2025 Strategic Plan

    The purpose of the CISA Strategic Plan is to communicate the...

    Continuous Risk Improvement? Q3 Cyber Round-Up From Cowbell Cyber

    According to Manu Singh, director of risk engineering at Cowbell, "Every...

    A Comprehensive Cyber Discovery Resource? The DoD Cybersecurity Policy Chart from CSIAC

    The Cyber Security and Information Systems Information Analysis Center (CSIAC) is...

    Rapidly Evolving Cyber Insurance? Q2 Cyber Round-Up From Cowbell Cyber

    According to Isabelle Dumont, SVP of Marketing and Technology Partners at...

    Revealing Response? Nuix Responds to ASX Request for Information

    The following investor news update from Nuix shares a written response...

    Revealing Reports? Nuix Notes Press Speculation

    According to a September 9, 2022 market release from Nuix, the...

    Regards to Broadway? HaystackID® Acquires Business Intelligence Associates

    According to HaystackID CEO Hal Brooks, “BIA is a leader in...

    One Large Software and Cloud Business? OpenText to Acquire Micro Focus

    According to OpenText CEO & CTO Mark J. Barrenechea, “We are...

    On the Move? 2022 eDiscovery Market Kinetics: Five Areas of Interest

    Recently ComplexDiscovery was provided an opportunity to share with the eDiscovery...

    Trusting the Process? 2021 eDiscovery Processing Task, Spend, and Cost Data Points

    Based on the complexity of cybersecurity, information governance, and legal discovery,...

    The Year in Review? 2021 eDiscovery Review Task, Spend, and Cost Data Points

    Based on the complexity of cybersecurity, information governance, and legal discovery,...

    A 2021 Look at eDiscovery Collection: Task, Spend, and Cost Data Points

    Based on the complexity of cybersecurity, information governance, and legal discovery,...

    Five Great Reads on Cyber, Data, and Legal Discovery for September 2022

    From privacy legislation and special masters to acquisitions and investigations, the...

    Five Great Reads on Cyber, Data, and Legal Discovery for August 2022

    From AI and Big Data challenges to intriguing financial and investment...

    Five Great Reads on Cyber, Data, and Legal Discovery for July 2022

    From lurking business undercurrents to captivating deepfake developments, the July 2022...

    Five Great Reads on Cyber, Data, and Legal Discovery for June 2022

    From eDiscovery ecosystem players and pricing to data breach investigations and...

    Cooler Temperatures? Fall 2022 eDiscovery Business Confidence Survey Results

    Since January 2016, 2,874 individual responses to twenty-eight quarterly eDiscovery Business...

    Inflection or Deflection? An Aggregate Overview of Eight Semi-Annual eDiscovery Pricing Surveys

    Initiated in the winter of 2019 and conducted eight times with...

    Changing Currents? Eighteen Observations on eDiscovery Business Confidence in the Summer of 2022

    In the summer of 2022, 54.8% of survey respondents felt that...

    Challenging Variants? Issues Impacting eDiscovery Business Performance: A Summer 2022 Overview

    In the summer of 2022, 28.8% of respondents viewed increasing types...

    Nuclear Options? Ukraine Conflict Assessments in Maps (September 17 – 21, 2022)

    According to a recent update from the Institute for the Study...

    Mass Graves and Torture Chambers? Ukraine Conflict Assessments in Maps (September 12 – 16, 2022)

    According to a recent update from the Institute for the Study...

    On The Run? Ukraine Conflict Assessments in Maps (September 7 – 11, 2022)

    According to a recent update from the Institute for the Study...

    Tangible Degradation? Ukraine Conflict Assessments in Maps (September 2 – 6, 2022)

    According to a recent update from the Institute for the Study...