Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attribution Methods

2024-05-02

arXiv.org

AI Summary

Existing attribution methods lack ground-truth causal explanations, rendering faithfulness evaluation unreliable. Method: This paper introduces BackX, a high-fidelity explainable AI benchmark that—uniquely—injects controllable causal attribution signals via backdoor triggers, rigorously satisfying faithfulness criteria including completeness, causality, and controllability. Contribution/Results: We provide theoretical guarantees that BackX outperforms both synthetic and real-world benchmarks in faithfulness assessment. We establish a standardized evaluation protocol incorporating attribution post-processing and cross-model consistency analysis. Empirically, BackX enables reproducible, high-discriminative evaluation across 12 state-of-the-art attribution methods, systematically exposing their causal faithfulness deficiencies. Furthermore, it inspires a novel attribution-based backdoor detection paradigm.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Attribution methods compute importance scores for input features to explain the output predictions of deep models. However, accurate assessment of attribution methods is challenged by the lack of benchmark fidelity for attributing model predictions. Moreover, other confounding factors in attribution estimation, including the setup choices of post-processing techniques and explained model predictions, further compromise the reliability of the evaluation. In this work, we first identify a set of fidelity criteria that reliable benchmarks for attribution methods are expected to fulfill, thereby facilitating a systematic assessment of attribution benchmarks. Next, we introduce a Backdoor-based eXplainable AI benchmark (BackX) that adheres to the desired fidelity criteria. We theoretically establish the superiority of our approach over the existing benchmarks for well-founded attribution evaluation. With extensive analysis, we also identify a setup for a consistent and fair benchmarking of attribution methods across different underlying methodologies. This setup is ultimately employed for a comprehensive comparison of existing methods using our BackX benchmark. Finally, our analysis also provides guidance for defending against backdoor attacks with the help of attribution methods.

Problem

• Evaluating faithfulness of attribution methods without ground truth
• Developing benchmark criteria for systematic attribution assessment
• Establishing standardized evaluation setup to mitigate confounding factors

Innovation

• Backdoor-based benchmark for explainable AI evaluation
• Theoretical superiority over existing attribution benchmarks
• Standardized setup mitigating post-processing confounding factors