# A Generative Victim Model for Segmentation

arXiv: https://arxiv.org/abs/2412.07274 · HTML: https://mlsanity.com/paper/2412.07274/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 89 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 7 of 7)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [Guided Diffusion Model for Adversarial Purification](https://mlsanity.com/paper/2205.14969/) (2022)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [Adversarial Examples on Segmentation Models Can be Easy to Transfer](https://mlsanity.com/paper/2111.11368/) (2021)

## Abstract (arXiv)

We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is needed to generate attacks for segmentation. In this context, the victim model is assumed to be robust to achieve effective adversarial perturbation generation. Instead of focusing on improving the robustness of the task-specific victim models, we shift our attention to image generation. From an image generation perspective, we derive a novel VM for segmentation, aiming to generate adversarial perturbations for segmentation tasks without requiring models explicitly designed for image segmentation. Our approach to adversarial attack generation diverges from conventional white-box or black-box attacks, offering a fresh outlook on adversarial attack strategies. Experiments show that our attack method is able to generate effective adversarial attacks with good transferability.