# Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples

arXiv: https://arxiv.org/abs/2403.05181 · HTML: https://mlsanity.com/paper/2403.05181/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 26 references that are in the map.
- First posted on arXiv 8 Mar 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Embedding Watermarks into Deep Neural Networks](https://mlsanity.com/paper/1701.04082/) (2017)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks](https://mlsanity.com/paper/1909.07830/) (2019)
- [Heterogeneous Knowledge Distillation using Information Flow Modeling](https://mlsanity.com/paper/2005.00727/) (2020)
- [Learning Student Networks via Feature Embedding](https://mlsanity.com/paper/1812.06597/) (2018)
- [Passport-aware Normalization for Deep Model Protection](https://mlsanity.com/paper/2010.15824/) (2020)
- [Undistillable: Making A Nasty Teacher That CANNOT teach students](https://mlsanity.com/paper/2105.07381/) (2021)
- [Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluations](https://mlsanity.com/paper/2011.13564/) (2020)

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

- [The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model](https://mlsanity.com/paper/2501.16226/) (2025)
- [ADS-C: Antidistillation Sampling for Classification](https://mlsanity.com/paper/2607.15467/) (2026)

## Abstract (arXiv)

We introduce Adversarial Sparse Teacher (AST), a robust defense method against distillation-based model stealing attacks. Our approach trains a teacher model using adversarial examples to produce sparse logit responses and increase the entropy of the output distribution. Typically, a model generates a peak in its output corresponding to its prediction. By leveraging adversarial examples, AST modifies the teacher model's original response, embedding a few altered logits into the output while keeping the primary response slightly higher. Concurrently, all remaining logits are elevated to further increase the output distribution's entropy. All these complex manipulations are performed using an optimization function with our proposed Exponential Predictive Divergence (EPD) loss function. EPD allows us to maintain higher entropy levels compared to traditional KL divergence, effectively confusing attackers. Experiments on CIFAR-10 and CIFAR-100 datasets demonstrate that AST outperforms state-of-the-art methods, providing effective defense against model stealing while preserving high accuracy. The source codes will be made publicly available here soon.