# Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once

arXiv: https://arxiv.org/abs/1908.05185 · HTML: https://mlsanity.com/paper/1908.05185/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [A Survey on Transferability of Adversarial Examples across Deep Neural Networks](https://mlsanity.com/paper/2310.17626/) (2023)
- [Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks](https://mlsanity.com/paper/2107.01809/) (2021)
- [CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks](https://mlsanity.com/paper/2407.10179/) (2024)
- [GAMA: Generative Adversarial Multi-Object Scene Attacks](https://mlsanity.com/paper/2209.09502/) (2022)
- [Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing](https://mlsanity.com/paper/2105.07553/) (2021)
- [Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real World](https://mlsanity.com/paper/2310.16061/) (2023)
- [Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks](https://mlsanity.com/paper/2209.09883/) (2022)
- [Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection](https://mlsanity.com/paper/2407.12292/) (2024)
- [Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization](https://mlsanity.com/paper/2502.02096/) (2025)
- [Towards Cross-Domain Multi-Targeted Adversarial Attacks](https://mlsanity.com/paper/2505.20782/) (2025)

## Abstract (arXiv)

Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods. However, current generation-based methods are only able to attack one specific target (category) within one model, thus making them not applicable to real classification systems that often have hundreds/thousands of categories. In this paper, we propose the first Multi-target Adversarial Network (MAN), which can generate multi-target adversarial samples with a single model. By incorporating the specified category information into the intermediate features, it can attack any category of the target classification model during runtime. Experiments show that the proposed MAN can produce stronger attack results and also have better transferability than previous state-of-the-art methods in both multi-target attack task and single-target attack task. We further use the adversarial samples generated by our MAN to improve the robustness of the classification model. It can also achieve better classification accuracy than other methods when attacked by various methods.