Hacking a surrogate model approach to XAI

• URL: http://arxiv.org/abs/2406.16626v1
• Date: Mon, 24 Jun 2024 13:18:02 GMT
• Title: Hacking a surrogate model approach to XAI
• Authors: Alexander Wilhelm, Katharina A. Zweig,
• Abstract summary: We show that even if a discriminated subgroup does not get a positive decision from the black box ADM system, the corresponding question of group membership can be pushed down onto a level as low as wanted. Our approach can be generalized easily to other surrogate models.
• Score: 49.1574468325115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, the number of new applications for highly complex AI systems has risen significantly. Algorithmic decision-making systems (ADMs) are one of such applications, where an AI system replaces the decision-making process of a human expert. As one approach to ensure fairness and transparency of such systems, explainable AI (XAI) has become more important. One variant to achieve explainability are surrogate models, i.e., the idea to train a new simpler machine learning model based on the input-output-relationship of a black box model. The simpler machine learning model could, for example, be a decision tree, which is thought to be intuitively understandable by humans. However, there is not much insight into how well the surrogate model approximates the black box. Our main assumption is that a good surrogate model approach should be able to bring such a discriminating behavior to the attention of humans; prior to our research we assumed that a surrogate decision tree would identify such a pattern on one of its first levels. However, in this article we show that even if the discriminated subgroup - while otherwise being the same in all categories - does not get a single positive decision from the black box ADM system, the corresponding question of group membership can be pushed down onto a level as low as wanted by the operator of the system. We then generalize this finding to pinpoint the exact level of the tree on which the discriminating question is asked and show that in a more realistic scenario, where discrimination only occurs to some fraction of the disadvantaged group, it is even more feasible to hide such discrimination. Our approach can be generalized easily to other surrogate models.

Related papers

• Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes [73.12947922129261]
  We leverage the zero-shot capabilities of large language models to reduce stereotyping. We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
  arXiv  Detail & Related papers  (2024-02-03T01:40:11Z)
• CLIMAX: An exploration of Classifier-Based Contrastive Explanations [5.381004207943597]
  We propose a novel post-hoc model XAI technique that provides contrastive explanations justifying the classification of a black box. Our method, which we refer to as CLIMAX, is based on local classifiers. We show that we achieve better consistency as compared to baselines such as LIME, BayLIME, and SLIME.
  arXiv  Detail & Related papers  (2023-07-02T22:52:58Z)
• Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses [45.720065723998225]
  We introduce a new task, "less likely brainstorming," that asks a model to generate outputs that humans think are relevant but less likely to happen. We find that a baseline approach of training with less likely hypotheses as targets generates outputs that humans evaluate as either likely or irrelevant nearly half of the time. We propose a controlled text generation method that uses a novel contrastive learning strategy to encourage models to differentiate between generating likely and less likely outputs according to humans.
  arXiv  Detail & Related papers  (2023-05-30T18:05:34Z)
• Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment [66.91538273487379]
  There is a certain consensus about the need to develop AI applications with a Human-Centric approach. Human-Centric Machine Learning needs to be developed based on four main requirements: (i) utility and social good; (ii) privacy and data ownership; (iii) transparency and accountability; and (iv) fairness in AI-driven decision-making processes. We study how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data.
  arXiv  Detail & Related papers  (2023-02-13T16:44:44Z)
• Certifying Fairness of Probabilistic Circuits [33.1089249944851]
  We propose an algorithm to search for discrimination patterns in a general class of probabilistic models, namely probabilistic circuits. We also introduce new classes of patterns such as minimal, maximal, and optimal patterns that can effectively summarize exponentially many discrimination patterns.
  arXiv  Detail & Related papers  (2022-12-05T18:36:45Z)
• Revealing Unfair Models by Mining Interpretable Evidence [50.48264727620845]
  The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications. In this paper, we tackle the novel task of revealing unfair models by mining interpretable evidence. Our method finds highly interpretable and solid evidence to effectively reveal the unfairness of trained models.
  arXiv  Detail & Related papers  (2022-07-12T20:03:08Z)
• Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation [55.27563366506407]
  We introduce a discriminator-free adversarial learning network (DALN) for unsupervised domain adaptation (UDA) DALN achieves explicit domain alignment and category distinguishment through a unified objective. DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets.
  arXiv  Detail & Related papers  (2022-04-08T04:40:18Z)
• Explainability for identification of vulnerable groups in machine learning models [1.7403133838762446]
  Machine learning fairness as a field is focused on the just treatment of individuals and groups under information processing. This raises new challenges on how and when to protect vulnerable individuals and groups under machine learning. Neither existing fairness nor existing explainability methods allow us to ascertain if a prediction model identifies vulnerability.
  arXiv  Detail & Related papers  (2022-03-01T09:44:19Z)
• Augmented Fairness: An Interpretable Model Augmenting Decision-Makers' Fairness [10.53972370889201]
  We propose a model-agnostic approach for mitigating the prediction bias of a black-box decision-maker. Our method detects in the feature space where the black-box decision-maker is biased and replaces it with a few short decision rules, acting as a "fair surrogate"
  arXiv  Detail & Related papers  (2020-11-17T03:25:44Z)
• Bias in Multimodal AI: Testbed for Fair Automatic Recruitment [73.85525896663371]
  We study how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data. We train automatic recruitment algorithms using a set of multimodal synthetic profiles consciously scored with gender and racial biases. Our methodology and results show how to generate fairer AI-based tools in general, and in particular fairer automated recruitment systems.
  arXiv  Detail & Related papers  (2020-04-15T15:58:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.