# Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv: https://arxiv.org/abs/2307.07873 · HTML: https://mlsanity.com/paper/2307.07873/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 100 references that are in the map.
- First posted on arXiv 15 Jul 2023.

## Builds on (most cited first, 30 of 74)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [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)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality](https://mlsanity.com/paper/1801.02613/) (2018)
- [When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations](https://mlsanity.com/paper/2106.01548/) (2021)
- [PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples](https://mlsanity.com/paper/1710.10766/) (2017)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [On the Origin of Implicit Regularization in Stochastic Gradient Descent](https://mlsanity.com/paper/2101.12176/) (2021)
- [Spectral Norm Regularization for Improving the Generalizability of Deep Learning](https://mlsanity.com/paper/1705.10941/) (2017)
- [Disentangling Adversarial Robustness and Generalization](https://mlsanity.com/paper/1812.00740/) (2018)
- [Surrogate Gap Minimization Improves Sharpness-Aware Training](https://mlsanity.com/paper/2203.08065/) (2022)
- [Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets](https://mlsanity.com/paper/2002.05990/) (2020)
- [On the Robustness of Vision Transformers to Adversarial Examples](https://mlsanity.com/paper/2104.02610/) (2021)
- [Implicit Gradient Regularization](https://mlsanity.com/paper/2009.11162/) (2020)
- [Towards Understanding Sharpness-Aware Minimization](https://mlsanity.com/paper/2206.06232/) (2022)

## Built on by (most cited first, 30 of 32)

- [Downstream-agnostic Adversarial Examples](https://mlsanity.com/paper/2307.12280/) (2023)
- [DarkSAM: Fooling Segment Anything Model to Segment Nothing](https://mlsanity.com/paper/2409.17874/) (2024)
- [Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples](https://mlsanity.com/paper/2403.10801/) (2024)
- [Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks](https://mlsanity.com/paper/2405.12725/) (2024)
- [Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack](https://mlsanity.com/paper/2411.02669/) (2024)
- [NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors](https://mlsanity.com/paper/2412.16955/) (2024)
- [Bag of Tricks to Boost Adversarial Transferability](https://mlsanity.com/paper/2401.08734/) (2024)
- [Improving Adversarial Transferability via Model Alignment](https://mlsanity.com/paper/2311.18495/) (2023)
- [ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification](https://mlsanity.com/paper/2406.15093/) (2024)
- [Scaling Laws for Black box Adversarial Attacks](https://mlsanity.com/paper/2411.16782/) (2024)
- [Boosting Adversarial Transferability with Low-Cost Optimization via Maximin Expected Flatness](https://mlsanity.com/paper/2405.16181/) (2024)
- [Understanding Model Ensemble in Transferable Adversarial Attack](https://mlsanity.com/paper/2410.06851/) (2024)
- [FLARE: Toward Universal Dataset Purification against Backdoor Attacks](https://mlsanity.com/paper/2411.19479/) (2024)
- [Adversarial Example Soups: Improving Transferability and Stealthiness for Free](https://mlsanity.com/paper/2402.18370/) (2024)
- [A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures](https://mlsanity.com/paper/2404.00673/) (2024)
- [Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability](https://mlsanity.com/paper/2401.07087/) (2024)
- [Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack](https://mlsanity.com/paper/2509.23871/) (2025)
- [Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization](https://mlsanity.com/paper/2503.12793/) (2025)
- [Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving](https://mlsanity.com/paper/2404.11357/) (2024)
- [RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses](https://mlsanity.com/paper/2412.20987/) (2024)
- [Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking](https://mlsanity.com/paper/2504.05838/) (2025)
- [Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping](https://mlsanity.com/paper/2505.13182/) (2025)
- [GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors](https://mlsanity.com/paper/2506.08188/) (2025)
- [Towards Understanding Adversarial Transferability in Federated Learning](https://mlsanity.com/paper/2310.00616/) (2023)
- [Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR](https://mlsanity.com/paper/2401.17038/) (2024)
- [On the Adversarial Transferability of Generalized "Skip Connections"](https://mlsanity.com/paper/2410.08950/) (2024)
- [S4ST: A Strong, Self-transferable, faSt, and Simple Scale Transformation for Transferable Targeted Attack](https://mlsanity.com/paper/2410.13891/) (2024)
- [Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space](https://mlsanity.com/paper/2407.08572/) (2024)
- [Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing](https://mlsanity.com/paper/2408.12673/) (2024)
- [SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures](https://mlsanity.com/paper/2508.06127/) (2025)

## Abstract (arXiv)

Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable AEs, many of these findings lack explanations and even lead to inconsistent advice. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing little robustness phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates, we attribute it to a trade-off between two predominant factors: model smoothness and gradient similarity. Our investigations focus on their joint effects, rather than their separate correlations with transferability. Through a series of theoretical and empirical analyses, we conjecture that the data distribution shift in adversarial training explains the degradation of gradient similarity. Building on these insights, we explore the impacts of data augmentation and gradient regularization on transferability and identify that the trade-off generally exists in the various training mechanisms, thus building a comprehensive blueprint for the regulation mechanism behind transferability. Finally, we provide a general route for constructing better surrogates to boost transferability which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other, and emphasize the crucial role of manipulating surrogate models.