# Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks

arXiv: https://arxiv.org/abs/2212.09035 · HTML: https://mlsanity.com/paper/2212.09035/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 18 Dec 2022.

## Builds on (most cited first, 30 of 35)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets](https://mlsanity.com/paper/2002.05990/) (2020)
- [The Space of Transferable Adversarial Examples](https://mlsanity.com/paper/1704.03453/) (2017)
- [Admix: Enhancing the Transferability of Adversarial Attacks](https://mlsanity.com/paper/2102.00436/) (2021)
- [Generative Adversarial Perturbations](https://mlsanity.com/paper/1712.02328/) (2017)
- [Cross-Domain Transferability of Adversarial Perturbations](https://mlsanity.com/paper/1905.11736/) (2019)
- [On Success and Simplicity: A Second Look at Transferable Targeted Attacks](https://mlsanity.com/paper/2012.11207/) (2020)
- [Backpropagating Linearly Improves Transferability of Adversarial Examples](https://mlsanity.com/paper/2012.03528/) (2020)
- [On Generating Transferable Targeted Perturbations](https://mlsanity.com/paper/2103.14641/) (2021)
- [Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability](https://mlsanity.com/paper/2004.14861/) (2020)

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

- [A Survey on Transferability of Adversarial Examples across Deep Neural Networks](https://mlsanity.com/paper/2310.17626/) (2023)
- [Bag of Tricks to Boost Adversarial Transferability](https://mlsanity.com/paper/2401.08734/) (2024)
- [As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?](https://mlsanity.com/paper/2403.12693/) (2024)
- [MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models](https://mlsanity.com/paper/2506.02362/) (2025)
- [Understanding Model Ensemble in Transferable Adversarial Attack](https://mlsanity.com/paper/2410.06851/) (2024)
- [Improving the Transferability of Adversarial Examples by Feature Augmentation](https://mlsanity.com/paper/2407.06714/) (2024)
- [Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection](https://mlsanity.com/paper/2407.12292/) (2024)
- [Detecting Adversarial Data using Perturbation Forgery](https://mlsanity.com/paper/2405.16226/) (2024)
- [S4ST: A Strong, Self-transferable, faSt, and Simple Scale Transformation for Transferable Targeted Attack](https://mlsanity.com/paper/2410.13891/) (2024)
- [PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage](https://mlsanity.com/paper/2504.11509/) (2025)
- [Enhancing Transferability of Targeted Adversarial Examples: A Self-Universal Perspective](https://mlsanity.com/paper/2407.15683/) (2024)
- [Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach](https://mlsanity.com/paper/2504.14137/) (2025)
- [Improving Black-Box Generative Attacks via Generator Semantic Consistency](https://mlsanity.com/paper/2506.18248/) (2025)
- [Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation](https://mlsanity.com/paper/2602.23117/) (2026)

## Abstract (arXiv)

In this work, we study the black-box targeted attack problem from the model discrepancy perspective. On the theoretical side, we present a generalization error bound for black-box targeted attacks, which gives a rigorous theoretical analysis for guaranteeing the success of the attack. We reveal that the attack error on a target model mainly depends on empirical attack error on the substitute model and the maximum model discrepancy among substitute models. On the algorithmic side, we derive a new algorithm for black-box targeted attacks based on our theoretical analysis, in which we additionally minimize the maximum model discrepancy(M3D) of the substitute models when training the generator to generate adversarial examples. In this way, our model is capable of crafting highly transferable adversarial examples that are robust to the model variation, thus improving the success rate for attacking the black-box model. We conduct extensive experiments on the ImageNet dataset with different classification models, and our proposed approach outperforms existing state-of-the-art methods by a significant margin. Our codes will be released.