# White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks

arXiv: https://arxiv.org/abs/1904.02405 · HTML: https://mlsanity.com/paper/1904.02405/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 14 of 14)

- [Knowledge Distillation as Semiparametric Inference](https://mlsanity.com/paper/2104.09732/) (2021)
- [Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution](https://mlsanity.com/paper/2210.17004/) (2022)
- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)
- [Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training](https://mlsanity.com/paper/2104.08645/) (2021)
- [A Differentiable Language Model Adversarial Attack on Text Classifiers](https://mlsanity.com/paper/2107.11275/) (2021)
- [ProTransformer: Robustify Transformers via Plug-and-Play Paradigm](https://mlsanity.com/paper/2410.23182/) (2024)
- [FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness](https://mlsanity.com/paper/2211.00294/) (2022)
- [Don't sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attacks](https://mlsanity.com/paper/2205.01714/) (2022)
- [The Impact of Quantization on the Robustness of Transformer-based Text Classifiers](https://mlsanity.com/paper/2403.05365/) (2024)
- [Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks](https://mlsanity.com/paper/2402.09874/) (2024)
- [Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries](https://mlsanity.com/paper/2508.10039/) (2025)
- [SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text](https://mlsanity.com/paper/2110.05748/) (2021)
- [SenTest: Evaluating Robustness of Sentence Encoders](https://mlsanity.com/paper/2311.17722/) (2023)
- [Adversarial Testing for Visual Grounding via Image-Aware Property Reduction](https://mlsanity.com/paper/2403.01118/) (2024)

## Abstract (arXiv)

Adversarial examples are important for understanding the behavior of neural models, and can improve their robustness through adversarial training. Recent work in natural language processing generated adversarial examples by assuming white-box access to the attacked model, and optimizing the input directly against it (Ebrahimi et al., 2018). In this work, we show that the knowledge implicit in the optimization procedure can be distilled into another more efficient neural network. We train a model to emulate the behavior of a white-box attack and show that it generalizes well across examples. Moreover, it reduces adversarial example generation time by 19x-39x. We also show that our approach transfers to a black-box setting, by attacking The Google Perspective API and exposing its vulnerability. Our attack flips the API-predicted label in 42% of the generated examples, while humans maintain high-accuracy in predicting the gold label.