# From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation

arXiv: https://arxiv.org/abs/2412.05592 · HTML: https://mlsanity.com/paper/2412.05592/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 55 references that are in the map.
- First posted on arXiv 7 Dec 2024.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques](https://mlsanity.com/paper/1909.03012/) (2019)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI](https://mlsanity.com/paper/2003.07258/) (2020)
- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)
- [Sanity Checks for Saliency Metrics](https://mlsanity.com/paper/1912.01451/) (2019)
- [A Consistent and Efficient Evaluation Strategy for Attribution Methods](https://mlsanity.com/paper/2202.00449/) (2022)
- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [On quantitative aspects of model interpretability](https://mlsanity.com/paper/2007.07584/) (2020)
- [Framework for Evaluating Faithfulness of Local Explanations](https://mlsanity.com/paper/2202.00734/) (2022)
- [IROF: a low resource evaluation metric for explanation methods](https://mlsanity.com/paper/2003.08747/) (2020)
- [The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus](https://mlsanity.com/paper/2302.07265/) (2023)
- [NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights](https://mlsanity.com/paper/2106.10185/) (2021)
- [Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks](https://mlsanity.com/paper/2401.06654/) (2024)
- [Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations](https://mlsanity.com/paper/2211.12486/) (2022)
- [On the Relationship Between Explanation and Prediction: A Causal View](https://mlsanity.com/paper/2212.06925/) (2022)

## Built on by (most cited first, 4 of 4)

- [Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance](https://mlsanity.com/paper/2502.04695/) (2025)
- [The Role of Hyperparameters in Predictive Multiplicity](https://mlsanity.com/paper/2503.13506/) (2025)
- [Position: Explainable AI is Causality in Disguise](https://mlsanity.com/paper/2603.28597/) (2026)
- [Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition](https://mlsanity.com/paper/2609.33486/) (2026)

## Abstract (arXiv)

The lack of ground truth explanation labels is a fundamental challenge for quantitative evaluation in explainable artificial intelligence (XAI). This challenge becomes especially problematic when evaluation methods have numerous hyperparameters that must be specified by the user, as there is no ground truth to determine an optimal hyperparameter selection. It is typically not feasible to do an exhaustive search of hyperparameters so researchers typically make a normative choice based on similar studies in the literature, which provides great flexibility for the user. In this work, we illustrate how this flexibility can be exploited to manipulate the evaluation outcome. We frame this manipulation as an adversarial attack on the evaluation where seemingly innocent changes in hyperparameter setting significantly influence the evaluation outcome. We demonstrate the effectiveness of our manipulation across several datasets with large changes in evaluation outcomes across several explanation methods and models. Lastly, we propose a mitigation strategy based on ranking across hyperparameters that aims to provide robustness towards such manipulation. This work highlights the difficulty of conducting reliable XAI evaluation and emphasizes the importance of a holistic and transparent approach to evaluation in XAI.