# Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attacks

arXiv: https://arxiv.org/abs/2505.03435 · HTML: https://mlsanity.com/paper/2505.03435/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 27 of 27)

- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Better Diffusion Models Further Improve Adversarial Training](https://mlsanity.com/paper/2302.04638/) (2023)
- [Exploiting Style Latent Flows for Generalizing Deepfake Video Detection](https://mlsanity.com/paper/2403.06592/) (2024)
- [AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection](https://mlsanity.com/paper/2406.02951/) (2024)
- [Generalizable Synthetic Image Detection via Language-guided Contrastive Learning](https://mlsanity.com/paper/2305.13800/) (2023)
- [Lighting (In)consistency of Paint by Text](https://mlsanity.com/paper/2207.13744/) (2022)
- [ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detection](https://mlsanity.com/paper/2302.11970/) (2023)
- [Perspective (In)consistency of Paint by Text](https://mlsanity.com/paper/2206.14617/) (2022)
- [Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attacks](https://mlsanity.com/paper/1803.00401/) (2018)
- [Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes](https://mlsanity.com/paper/2304.06470/) (2023)
- [Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis](https://mlsanity.com/paper/2303.10762/) (2023)
- [Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities](https://mlsanity.com/paper/2407.20337/) (2024)
- [Learning Natural Consistency Representation for Face Forgery Video Detection](https://mlsanity.com/paper/2407.10550/) (2024)
- [Analyzing Fairness in Deepfake Detection With Massively Annotated Databases](https://mlsanity.com/paper/2208.05845/) (2022)
- [Perturbation Inactivation Based Adversarial Defense for Face Recognition](https://mlsanity.com/paper/2207.06035/) (2022)

## Abstract (arXiv)

The rapid advancement of generative image technology has introduced significant security concerns, particularly in the domain of face generation detection. This paper investigates the vulnerabilities of current AI-generated face detection systems. Our study reveals that while existing detection methods often achieve high accuracy under standard conditions, they exhibit limited robustness against adversarial attacks. To address these challenges, we propose an approach that integrates adversarial training to mitigate the impact of adversarial examples. Furthermore, we utilize diffusion inversion and reconstruction to further enhance detection robustness. Experimental results demonstrate that minor adversarial perturbations can easily bypass existing detection systems, but our method significantly improves the robustness of these systems. Additionally, we provide an in-depth analysis of adversarial and benign examples, offering insights into the intrinsic characteristics of AI-generated content. All associated code will be made publicly available in a dedicated repository to facilitate further research and verification.