FlowCrypt: Flow-Based Lightweight Encryption with Near-Lossless Recovery for Cloud Photo Privacy

2025-09-23

AI Summary

To address the challenge of simultaneously ensuring privacy preservation and high-fidelity reconstruction in cloud-based photo storage, this paper proposes a lightweight, flow-based reversible image encryption framework. Methodologically, it departs from conventional CNN/GAN-based or reference-image-dependent invertible neural network (INN) approaches, introducing instead a novel key-conditioned random tiling scheme coupled with an end-to-end reversible neural architecture. Encryption and decryption are jointly optimized via parameter-shared, flow-based invertible modules (FED), fully preserving auxiliary information. Contributions include: (i) the first reference-free near-lossless reconstruction (PSNR ≈ 100 dB); (ii) statistically uniform ciphertexts with strong cryptographic security; and (iii) an ultra-compact model (≈1M parameters), drastically reducing computational overhead on edge devices. Extensive evaluation across three benchmark datasets confirms its efficiency, robustness, and practical applicability.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Privacy
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Applications of cryptography
• Responsible Web: Measurement, analysis, and circumvention of Web censorship
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The widespread adoption of smartphone photography has led users to increasingly rely on cloud storage for personal photo archiving and sharing, raising critical privacy concerns. Existing deep learning-based image encryption schemes, typically built upon CNNs or GANs, often depend on traditional cryptographic algorithms and lack inherent architectural reversibility, resulting in limited recovery quality and poor robustness. Invertible neural networks (INNs) have emerged to address this issue by enabling reversible transformations, yet the first INN-based encryption scheme still relies on an auxiliary reference image and discards by-product information before decryption, leading to degraded recovery and limited practicality. To address these limitations, this paper proposes FlowCrypt, a novel flow-based image encryption framework that simultaneously achieves near-lossless recovery, high security, and lightweight model design. FlowCrypt begins by applying a key-conditioned random split to the input image, enhancing forward-process randomness and encryption strength. The resulting components are processed through a Flow-based Encryption/Decryption (FED) module composed of invertible blocks, which share parameters across encryption and decryption. Thanks to its reversible architecture and reference-free design, FlowCrypt ensures high-fidelity image recovery. Extensive experiments show that FlowCrypt achieves recovery quality with 100dB on three datasets, produces uniformly distributed cipher images, and maintains a compact architecture with only 1M parameters, making it suitable for mobile and edge-device applications.

Problem

• Protecting cloud photo privacy with lightweight encryption
• Achieving near-lossless image recovery after decryption
• Overcoming limitations of existing deep learning encryption methods

Innovation

• Flow-based encryption with invertible neural networks
• Key-conditioned random split for enhanced security
• Reference-free design enabling near-lossless image recovery