# Towards Good Practices in Evaluating Transfer Adversarial Attacks

arXiv: https://arxiv.org/abs/2211.09565 · HTML: https://mlsanity.com/paper/2211.09565/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 88 of its 107 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Builds on (most cited first, 30 of 88)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)

## Built on by (most cited first, 15 of 15)

- [A Survey on Transferability of Adversarial Examples across Deep Neural Networks](https://mlsanity.com/paper/2310.17626/) (2023)
- [Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis](https://mlsanity.com/paper/2306.07754/) (2023)
- [Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models](https://mlsanity.com/paper/2308.07847/) (2023)
- [PubDef: Defending Against Transfer Attacks From Public Models](https://mlsanity.com/paper/2310.17645/) (2023)
- [SoK: Pitfalls in Evaluating Black-Box Attacks](https://mlsanity.com/paper/2310.17534/) (2023)
- [Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly](https://mlsanity.com/paper/2311.01323/) (2023)
- [Improving Transferability of Adversarial Examples via Bayesian Attacks](https://mlsanity.com/paper/2307.11334/) (2023)
- [Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection](https://mlsanity.com/paper/2309.01104/) (2023)
- [Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment](https://mlsanity.com/paper/2407.12401/) (2024)
- [Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability](https://mlsanity.com/paper/2304.02688/) (2023)
- [Rethinking PGD Attack: Is Sign Function Necessary?](https://mlsanity.com/paper/2312.01260/) (2023)
- [How to choose your best allies for a transferable attack?](https://mlsanity.com/paper/2304.02312/) (2023)
- [Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data](https://mlsanity.com/paper/2311.04503/) (2023)
- [On the Adversarial Transferability of Generalized "Skip Connections"](https://mlsanity.com/paper/2410.08950/) (2024)
- [Enhancing robustness of data-driven SHM models: adversarial training with circle loss](https://mlsanity.com/paper/2406.14232/) (2024)

## Abstract (arXiv)

Transfer adversarial attacks raise critical security concerns in real-world, black-box scenarios. However, the actual progress of this field is difficult to assess due to two common limitations in existing evaluations. First, different methods are often not systematically and fairly evaluated in a one-to-one comparison. Second, only transferability is evaluated but another key attack property, stealthiness, is largely overlooked. In this work, we design good practices to address these limitations, and we present the first comprehensive evaluation of transfer attacks, covering 23 representative attacks against 9 defenses on ImageNet. In particular, we propose to categorize existing attacks into five categories, which enables our systematic category-wise analyses. These analyses lead to new findings that even challenge existing knowledge and also help determine the optimal attack hyperparameters for our attack-wise comprehensive evaluation. We also pay particular attention to stealthiness, by adopting diverse imperceptibility metrics and looking into new, finer-grained characteristics. Overall, our new insights into transferability and stealthiness lead to actionable good practices for future evaluations.