AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs

Wenlong Cheng, Yuan Gan, Yunqiu Xu, Jiaxu Miao

ECCV 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Gradient inversion attacks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add negative Latent Vector Transformation (ablation)FedOT w/o LVT · LAION-10K (SD2.1 federated, after VAE replacement attack)FID after VAE replacement: 17.054 -> 40.537Improved
add translation Latent Vector Transformation (c=11) (ablation)FedOT w/o LVT · LAION-10K (SD2.1 federated, after VAE replacement attack)FID after VAE replacement: 17.054 -> 92.497Improved
add mirror Latent Vector Transformation (ablation)FedOT w/o LVT · LAION-10K (SD2.1 federated, after VAE replacement attack)FID after VAE replacement: 17.054 -> 70.622Improved
use deterministic negative transformation instead of random Gaussian noise (ablation)FedOT · LAION-10K (SD2.1 federated, no attack)FID: 35.585 -> 20.367Improved
add chunked watermark with client suffix bitsStable Signature* · LAION-10K client tracingDetection rate: -- -> 0.993Improved
add negative LVT to FedOT (ablation)FedOT w/o LVT · LAION-10K ownership verification (first 16 bits)Detection rate: 0.996 -> 0.960Hurt
add negative LVT to FedOT (ablation)FedOT w/o LVT · LAION-10K (SD2.1 federated, no attack)FID: 16.687 -> 20.367Hurt
increase translation coefficient c from 2 to 11 (ablation)FedOT_tran · LAION-10K (SD2.1 federated, after VAE replacement attack)FID increase under replacement attack: -1.424 -> +70.070Improved
increase translation coefficient c from 5 to 11 (ablation)FedOT_tran · LAION-10K (SD2.1 federated, no attack)FID: 19.684 -> 22.427Hurt
decrease lambda_i from 0.8 to 0.05 (ablation)watermarked VAE decoder · VAE decoder watermark fine-tuningPSNR vs bit accuracy: PSNR 34.793 -> 29.842; Bit Acc 0.906 -> 0.965Mixed
use r=16 instead of r=8 verification bits (ablation)FedOT_neg · LAION-10K ownership verification (first 16 bits)Detection rate: 0.944 -> 0.960Improved
use r=16 instead of r=24 verification bits (ablation)FedOT_neg · LAION-10K client tracing (last 32 bits)Bit accuracy: 0.899 -> 0.910Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy