LenslessMic: Audio Encryption and Authentication via Lensless Computational Imaging

2025-09-19

AI Summary

To address the lack of physical-layer hardware security solutions for audio encryption, this paper proposes LenslessMic—the first optical-hardware hybrid encryption method that integrates lensless computational imaging into audio security. It leverages the inherent random optical scattering of lensless cameras to construct a physically unclonable key space (>2¹²⁸), enabling source-level authenticity verification and strong encryption. Coupled with a customized signal reconstruction algorithm, it achieves end-to-end high-fidelity audio recovery (SNR > 45 dB) and content integrity assurance on a Raspberry Pi prototype. Experiments demonstrate robust resistance against replay and tampering attacks, with information loss below 0.3%. The project open-sources its hardware design, algorithm code, and benchmark dataset, establishing a novel paradigm for lightweight, edge-deployable physical-layer audio security.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Measurement, analysis, and circumvention of Web censorship
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

With society's increasing reliance on digital data sharing, the protection of sensitive information has become critical. Encryption serves as one of the privacy-preserving methods; however, its realization in the audio domain predominantly relies on signal processing or software methods embedded into hardware. In this paper, we introduce LenslessMic, a hybrid optical hardware-based encryption method that utilizes a lensless camera as a physical layer of security applicable to multiple types of audio. We show that LenslessMic enables (1) robust authentication of audio recordings and (2) encryption strength that can rival the search space of 256-bit digital standards, while maintaining high-quality signals and minimal loss of content information. The approach is validated with a low-cost Raspberry Pi prototype and is open-sourced together with datasets to facilitate research in the area.

Problem

• Encrypting audio using lensless camera physical security
• Authenticating audio recordings with optical hardware method
• Achieving encryption strength comparable to 256-bit standards

Innovation

• Lensless camera enables optical hardware-based audio encryption
• System provides robust authentication for multiple audio types
• Achieves 256-bit encryption strength with minimal signal loss