# Human-Imitating Metrics for Training and Evaluating Privacy Preserving Emotion Recognition Models Using Sociolinguistic Knowledge

arXiv: https://arxiv.org/abs/2104.08792 · HTML: https://mlsanity.com/paper/2104.08792/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Learning to Deceive with Attention-Based Explanations](https://mlsanity.com/paper/1909.07913/) (2019)
- [When Machine Learning Meets Privacy: A Survey and Outlook](https://mlsanity.com/paper/2011.11819/) (2020)
- [Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure](https://mlsanity.com/paper/1809.07424/) (2018)
- [Quantifying Interpretability and Trust in Machine Learning Systems](https://mlsanity.com/paper/1901.08558/) (2019)
- [Stakeholders in Explainable AI](https://mlsanity.com/paper/1810.00184/) (2018)
- [What are the biases in my word embedding?](https://mlsanity.com/paper/1812.08769/) (2018)
- [Speaker-Invariant Training via Adversarial Learning](https://mlsanity.com/paper/1804.00732/) (2018)
- [Privacy Enhanced Multimodal Neural Representations for Emotion Recognition](https://mlsanity.com/paper/1910.13212/) (2019)
- [Privacy-Preserving Image Classification in the Local Setting](https://mlsanity.com/paper/2002.03261/) (2020)
- [More Than Accuracy: Towards Trustworthy Machine Learning Interfaces for Object Recognition](https://mlsanity.com/paper/2008.01980/) (2020)

## Abstract (arXiv)

Privacy preservation is a crucial component of any real-world application. But, in applications relying on machine learning backends, privacy is challenging because models often capture more than what the model was initially trained for, resulting in the potential leakage of sensitive information. In this paper, we propose an automatic and quantifiable metric that allows us to evaluate humans' perception of a model's ability to preserve privacy with respect to sensitive variables. In this paper, we focus on saliency-based explanations, explanations that highlight regions of the input text, to infer internal workings of a black box model. We use the degree with which differences in interpretation of general vs privacy preserving models correlate with sociolinguistic biases to inform metric design. We show how certain commonly-used methods that seek to preserve privacy do not align with human perception of privacy preservation leading to distrust about model's claims. We demonstrate the versatility of our proposed metric by validating its utility for measuring cross corpus generalization for both privacy and emotion. Finally, we conduct crowdsourcing experiments to evaluate the inclination of the evaluators to choose a particular model for a given purpose when model explanations are provided, and show a positive relationship with the proposed metric. To the best of our knowledge, we take the first step in proposing automatic and quantifiable metrics that best align with human perception of model's ability for privacy preservation, allowing for cost-effective model development.