# Perturbation Effects on Robustness and Individual Fairness

arXiv: https://arxiv.org/abs/2404.01356 · HTML: https://mlsanity.com/paper/2404.01356/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Is Cosine-Similarity of Embeddings Really About Similarity?](https://mlsanity.com/paper/2403.05440/) (2024)
- [Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning](https://mlsanity.com/paper/2006.12621/) (2020)
- [DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones](https://mlsanity.com/paper/1909.04126/) (2019)
- [Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling](https://mlsanity.com/paper/2107.08176/) (2021)
- [Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity](https://mlsanity.com/paper/2203.07139/) (2022)
- [SeqLink: A Robust Neural-ODE Architecture for Modelling Partially Observed Time Series](https://mlsanity.com/paper/2212.03560/) (2022)
- [Equalised Odds is not Equal Individual Odds: Post-processing for Group and Individual Fairness](https://mlsanity.com/paper/2304.09779/) (2023)
- [How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies](https://mlsanity.com/paper/2207.04581/) (2022)

## Abstract (arXiv)

Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Robust Biased and Unrobust Fair behaviors. RIFair}reliably exposes these hidden vulnerabilities, supporting RIF as a necessary criterion for trustworthy model assessment. The experimental code is publicly available at https://github.com/Xuran-LI/RIFair.