skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: How to Explain and Justify Almost Any Decision: Potential Pitfalls for Accountability in AI Decision-Making
Discussion of the “right to an explanation” has been increasingly relevant because of its potential utility for auditing automated decision systems, as well as for making objections to such decisions. However, most existing work on explanations focuses on collaborative environments, where designers are motivated to implement good-faith explanations that reveal potential weaknesses of a decision system. This motivation may not hold in an auditing environment. Thus, we ask: how much could explanations be used maliciously to defend a decision system? In this paper, we demonstrate how a black-box explanation system developed to defend a black-box decision system could manipulate decision recipients or auditors into accepting an intentionally discriminatory decision model. In a case-by-case scenario where decision recipients are unable to share their cases and explanations, we find that most individual decision recipients could receive a verifiable justification, even if the decision system is intentionally discriminatory. In a system-wide scenario where every decision is shared, we find that while justifications frequently contradict each other, there is no intuitive threshold to determine if these contradictions are because of malicious justifications or because of simplicity requirements of these justifications conflicting with model behavior. We end with discussion of how system-wide metrics may be more useful than explanation systems for evaluating overall decision fairness, while explanations could be useful outside of fairness auditing.  more » « less
Award ID(s):
2008139
PAR ID:
10466323
Author(s) / Creator(s):
;
Date Published:
Journal Name:
ACM Conference on Fairness, Accountability and Transparency (FAccT)
Page Range / eLocation ID:
12 to 21
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, ACM Transactions on Human-Robot Interaction)
    null (Ed.)
    Explainability has emerged as a critical AI research objective, but the breadth of proposed methods and application domains suggest that criteria for explanation vary greatly. In particular, what counts as a good explanation, and what kinds of explanation are computationally feasible, has become trickier in light of oqaque “black box” systems such as deep neural networks. Explanation in such cases has drifted from what many philosophers stipulated as having to involve deductive and causal principles to mere “interpretation,” which approximates what happened in the target system to varying degrees. However, such post hoc constructed rationalizations are highly problematic for social robots that operate interactively in spaces shared with humans. For in such social contexts, explanations of behavior, and, in particular, justifications for violations of expected behavior, should make reference to socially accepted principles and norms. In this article, we show how a social robot’s actions can face explanatory demands for how it came to act on its decision, what goals, tasks, or purposes its design had those actions pursue and what norms or social constraints the system recognizes in the course of its action. As a result, we argue that explanations for social robots will need to be accurate representations of the system’s operation along causal, purposive, and justificatory lines. These explanations will need to generate appropriate references to principles and norms—explanations based on mere “interpretability” will ultimately fail to connect the robot’s behaviors to its appropriate determinants. We then lay out the foundations for a cognitive robotic architecture for HRI, together with particular component algorithms, for generating explanations and engaging in justificatory dialogues with human interactants. Such explanations track the robot’s actual decision-making and behavior, which themselves are determined by normative principles the robot can describe and use for justifications. 
    more » « less
  2. ; ; (, Proceedings of the ACM on Human-Computer Interaction)
    Social media platforms curate access to information and opportunities, and so play a critical role in shaping public discourse today. The opaque nature of the algorithms these platforms use to curate content raises societal questions. Prior studies have used black-box methods led by experts or collaborative audits driven by everyday users to show that these algorithms can lead to biased or discriminatory outcomes. However, existing auditing methods face fundamental limitations because they function independent of the platforms. Concerns of potential harmful outcomes have prompted proposal of legislation in both the U.S. and the E.U. to mandate a new form of auditing where vetted external researchers get privileged access to social media platforms. Unfortunately, to date there have been no concrete technical proposals to provide such auditing, because auditing at scale risks disclosure of users' private data and platforms' proprietary algorithms. We propose a new method for platform-supported auditing that can meet the goals of the proposed legislation. The first contribution of our work is to enumerate the challenges and the limitations of existing auditing methods to implement these policies at scale. Second, we suggest that limited, privileged access to relevance estimators is the key to enabling generalizable platform-supported auditing of social media platforms by external researchers. Third, we show platform-supported auditing need not risk user privacy nor disclosure of platforms' business interests by proposing an auditing framework that protects against these risks. For a particular fairness metric, we show that ensuring privacy imposes only a small constant factor increase (6.34x as an upper bound, and 4× for typical parameters) in the number of samples required for accurate auditing. Our technical contributions, combined with ongoing legal and policy efforts, can enable public oversight into how social media platforms affect individuals and society by moving past the privacy-vs-transparency hurdle. 
    more » « less
  3. ; ; (, Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23))
    The use of AI-based decision aids in diverse domains has inspired many empirical investigations into how AI models’ decision recommendations impact humans’ decision accuracy in AI-assisted decision making, while explorations on the impacts on humans’ decision fairness are largely lacking despite their clear importance. In this paper, using a real-world business decision making scenario—bidding in rental housing markets—as our testbed, we present an experimental study on understanding how the bias level of the AI-based decision aid as well as the provision of AI explanations affect the fairness level of humans’ decisions, both during and after their usage of the decision aid. Our results suggest that when people are assisted by an AI-based decision aid, both the higher level of racial biases the decision aid exhibits and surprisingly, the presence of AI explanations, result in more unfair human decisions across racial groups. Moreover, these impacts are partly made through triggering humans’ “disparate interactions” with AI. However, regardless of the AI bias level and the presence of AI explanations, when people return to make independent decisions after their usage of the AI-based decision aid, their decisions no longer exhibit significant unfairness across racial groups. 
    more » « less
  4. ; ; ; (, PMLR (Proceedings of Machine Learning Research))
    Neural networks have demonstrated a wide range of successes, but their “black box" nature raises concerns about transparency and reliability. Previous research on ReLU networks has sought to unwrap these networks into linear models based on activation states of all hidden units. In this paper, we introduce a novel approach that considers subsets of the hidden units involved in the decision making path. This pathwise explanation provides a clearer and more consistent understanding of the relationship between the input and the decision-making process. Our method also offers flexibility in adjusting the range of explanations within the input, i.e., from an overall attribution input to particular components within the input. Furthermore, it allows for the decomposition of explanations for a given input for more detailed explanations. Our experiments demonstrate that the proposed method outperforms existing methods both quantitatively and qualitatively. 
    more » « less
  5. ; ; (, ACM)
    Auditing social-media algorithms has become a focus of public-interest research and policymaking to ensure their fairness across demographic groups such as race, age, and gender in consequential domains such as the presentation of employment opportunities. However, such demographic attributes are often unavailable to auditors and platforms. When demographics data is unavailable, auditors commonly \emph{infer} them from other available information. In this work, we study the effects of inference error on auditing for bias in one prominent application: \emph{black-box} audit of ad delivery using \emph{paired ads}. We show that inference error, if not accounted for, causes auditing to falsely miss skew that exists. We then propose a way to mitigate the inference error when evaluating skew in ad delivery algorithms. Our method works by adjusting for expected error due to demographic inference, and it makes skew detection more sensitive when attributes must be inferred. Because inference is increasingly used for auditing, our results provide an important addition to the auditing toolbox to promote correct audits of ad delivery algorithms for bias. While the impact of attribute inference on accuracy has been studied in other domains, our work is the first to consider it for black-box evaluation of ad delivery bias, when only aggregate data is available to the auditor. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email