Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hiding
Jonggyu Jang, Hyeonsu Lyu, Seongjin Hwang, Hyun Jong Yang

TL;DR
This paper reveals vulnerabilities in adversarial visual information hiding by demonstrating a dual-strategy data reconstruction attack that can effectively recover encrypted images, challenging the security of current image encryption methods.
Contribution
Introduces a novel dual-strategy DR attack incorporating generative-adversarial and augmented identity loss to improve image reconstruction from encrypted data.
Findings
The attack significantly improves reconstructed image quality.
Fewer images need to share the same key model for security.
Results validated on image recognition and re-identification benchmarks.
Abstract
This paper investigates the security vulnerabilities of adversarial-example-based image encryption by executing data reconstruction (DR) attacks on encrypted images. A representative image encryption method is the adversarial visual information hiding (AVIH), which uses type-I adversarial example training to protect gallery datasets used in image recognition tasks. In the AVIH method, the type-I adversarial example approach creates images that appear completely different but are still recognized by machines as the original ones. Additionally, the AVIH method can restore encrypted images to their original forms using a predefined private key generative model. For the best security, assigning a unique key to each image is recommended; however, storage limitations may necessitate some images sharing the same key model. This raises a crucial security question for AVIH: How many images can…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Media Forensic Detection · Advanced Steganography and Watermarking Techniques · Adversarial Robustness in Machine Learning
