GoKawiilStealth Software and UVM Researchers Build ZK-JPEG to Verify Compressed Photo Authenticity
Researchers from Stealth Software Technologies and the University of Vermont have developed ZK-JPEG, a zero-knowledge cryptographic system that proves a JPEG image was correctly compressed from a genuine, committed source photo. The tool also supports common edits like blurring or redacting regions while still generating a valid proof, using the PicoZK framework to translate Python-based image editing into a zero-knowledge circuit built on line-point zero knowledge proofs.
GoKawiil's interpretation of the reporting above, not reported fact.
Existing camera-attestation and provenance-proof systems break down once an image undergoes standard lossy JPEG compression, leaving a major gap for verifying real-world photos shared online. By making authentication robust to compression and common edits, this work could give journalists, platforms, and forensic investigators a practical way to distinguish authentic camera footage from AI-generated deepfakes even after normal processing.
- ZK-JPEG lets provers verify JPEG compression happened correctly on a secret original image using zero-knowledge proofs.
- The system also supports common transformations like blurring or redaction without invalidating the proof.
- It's built with off-the-shelf tools, using PicoZK to convert Python image code into an LPZK-based ZK circuit.
Source: eprint.iacr.org — Samuel Dittmer, 2026-09-19
Published there as: “ZK-JPEG: Zero-Knowledge Image Editing and Compression”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.