AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learning

Tharindu Fernando, Clinton Fookes, Sridha Sridharan

TPAMI 2026 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 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 learnable directional embedding in the latent sphere (vs naive latent embedding) (ablation)DeepForgeSeal · CelebA-HQ validationBRA malicious: 0.42 -> 0.12Improved
add learnable directional embedding (vs naive latent embedding) (ablation)DeepForgeSeal · CelebA-HQ validationBRA benign: 0.78 -> 0.99Improved
add learnable directions (vs fixed directions) (ablation)DeepForgeSeal · CelebA-HQ validationBRA benign: 0.86 -> 0.99Improved
add learnable directional embedding (vs naive latent embedding) (ablation)DeepForgeSeal · CelebA-HQ validationPSNR: 46.23 -> 48.12Improved
add the attacker agent (ablation)DeepForgeSeal · CelebA-HQ validationBRA malicious: 0.59 -> 0.12Improved
add the attacker agent (ablation)DeepForgeSeal · CelebA-HQ validationPSNR: 32.11 -> 48.12Improved
use a learned combinatorial attack with adaptive curriculum (vs one fixed attack type) (ablation)DeepForgeSeal · CelebA-HQ validationBRA benign: 0.72 -> 0.99Improved
adapt the attack curriculum to the watermarker (vs predefined curriculum) (ablation)DeepForgeSeal · CelebA-HQ validationBRA malicious: 0.28 -> 0.12Improved
let a learnable agent compose attack sequences (vs random combinations) (ablation)DeepForgeSeal · CelebA-HQ validationBRA malicious: 0.31 -> 0.12Improved
add proximity and curiosity rewards (ablation)DeepForgeSeal · CelebA-HQ validationBRA malicious: 0.35 -> 0.12Improved
add curiosity reward to proximity reward (ablation)DeepForgeSeal · CelebA-HQ validationBRA malicious: 0.21 -> 0.12Improved
add proximity reward to curiosity reward (ablation)DeepForgeSeal · CelebA-HQ validationBRA malicious: 0.24 -> 0.12Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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