Authors

* External authors

Venue

Date

Share

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

Xiaoxiao Sun*

Nidham Gazagnadou

Vivek Sharma

Lingjuan Lyu

Hongdong Li*

Liang Zheng*

* External authors

NeurIPS 2023

2023

Abstract

Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally indicate more privacy leakage. Images determined as overall dissimilar, on the other hand, indicate higher robustness against attack. However, there is no guarantee that these metrics well reflect human opinions, which, as a judgement for model privacy leakage, are more trustworthy. In this paper, we comprehensively study the faithfulness of these hand-crafted metrics to human perception of privacy information from the reconstructed images. On 5 datasets ranging from natural images, faces, to fine-grained classes, we use 4 existing attack methods to reconstruct images from many different classification models and, for each reconstructed image, we ask multiple human annotators to assess whether this image is recognizable. Our studies reveal that the hand-crafted metrics only have a weak correlation with the human evaluation of privacy leakage and that even these metrics themselves often contradict each other. These observations suggest risks of current metrics in the community. To address this potential risk, we propose a learning-based measure called SemSim to evaluate the Semantic Similarity between the original and reconstructed images. SemSim is trained with a standard triplet loss, using an original image as an anchor, one of its recognizable reconstructed images as a positive sample, and an unrecognizable one as a negative. By training on human annotations, SemSim exhibits a greater reflection of privacy leakage on the semantic level. We show that SemSim has a significantly higher correlation with human judgment compared with existing metrics. Moreover, this strong correlation generalizes to unseen datasets, models and attack methods. We envision this work as a milestone for image quality evaluation closer to the human level. The project page is https://sites.google.com/view/semsim

Related Publications

How to Evaluate and Mitigate IP Infringement in Visual Generative AI?

ICML, 2025
Zhenting Wang, Chen Chen, Vikash Sehwag, Minzhou Pan*, Lingjuan Lyu

The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking r…

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models

CVPR, 2025
Jie Ren, Kangrui Chen, Yingqian Cui, Shenglai Zeng, Hui Liu, Yue Xing, Jiliang Tang, Lingjuan Lyu

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be exploited for malicious purposes, suc…

CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI

CVPR, 2025
Siyuan Cheng, Lingjuan Lyu, Zhenting Wang, Xiangyu Zhang, Vikash Sehwag

With the rapid advancement of generative AI, it is now pos-sible to synthesize high-quality images in a few seconds.Despite the power of these technologies, they raise signif-icant concerns regarding misuse. Current efforts to dis-tinguish between real and AI-generated image…

  • HOME
  • Publications
  • Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.