# Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysis

arXiv: https://arxiv.org/abs/2406.07820 · HTML: https://mlsanity.com/paper/2406.07820/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End](https://mlsanity.com/paper/2011.04917/) (2020)
- [A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations](https://mlsanity.com/paper/1805.07039/) (2018)
- [Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals](https://mlsanity.com/paper/2103.11972/) (2021)
- [Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice](https://mlsanity.com/paper/2103.14651/) (2021)
- [Exploring the Space of Adversarial Images](https://mlsanity.com/paper/1510.05328/) (2015)
- [Counterfactual Explanation Algorithms for Behavioral and Textual Data](https://mlsanity.com/paper/1912.01819/) (2019)
- [Contrastive Explanations in Neural Networks](https://mlsanity.com/paper/2008.00178/) (2020)
- [OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics](https://mlsanity.com/paper/2209.11195/) (2022)
- [Extracting Causal Visual Features for Limited label Classification](https://mlsanity.com/paper/2103.12322/) (2021)
- [Explanatory Paradigms in Neural Networks](https://mlsanity.com/paper/2202.11838/) (2022)
- [Probing the Purview of Neural Networks via Gradient Analysis](https://mlsanity.com/paper/2304.02834/) (2023)
- [VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability](https://mlsanity.com/paper/2406.00573/) (2024)

## Built on by (most cited first, 2 of 2)

- [Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability](https://mlsanity.com/paper/2512.06591/) (2025)
- [P-TAME: Explain Any Image Classifier with Trained Perturbations](https://mlsanity.com/paper/2501.17813/) (2025)

## Abstract (arXiv)

Explainable AI (XAI) has revolutionized the field of deep learning by empowering users to have more trust in neural network models. The field of XAI allows users to probe the inner workings of these algorithms to elucidate their decision-making processes. The rise in popularity of XAI has led to the advent of different strategies to produce explanations, all of which only occasionally agree. Thus several objective evaluation metrics have been devised to decide which of these modules give the best explanation for specific scenarios. The goal of the paper is twofold: (i) we employ the notions of necessity and sufficiency from causal literature to come up with a novel explanatory technique called SHifted Adversaries using Pixel Elimination(SHAPE) which satisfies all the theoretical and mathematical criteria of being a valid explanation, (ii) we show that SHAPE is, infact, an adversarial explanation that fools causal metrics that are employed to measure the robustness and reliability of popular importance based visual XAI methods. Our analysis shows that SHAPE outperforms popular explanatory techniques like GradCAM and GradCAM++ in these tests and is comparable to RISE, raising questions about the sanity of these metrics and the need for human involvement for an overall better evaluation.