RAW: Robust Avatar Watermarking -- Benchmarking and Baseline
Digital avatar watermarking presents unique challenges: avatars are routinely post-processed with background replacement, reframing, and format conversion before deployment. We introduce \textbf{RAW} (Robust Avatar Watermarking), a benchmark comprising 50 synthetic avatar videos from 5 commercial providers and 6 attacks simulating real-world avatar workflows. Evaluating 7 existing methods reveals that avatar-specific attacks such as background removal significantly degrade watermark recovery. We propose \textbf{WALT} (Watermarking Avatars with Learned Textures), which embeds watermarks in UV texture space via 3D face reconstruction. WALT achieves the highest robustness to zoom attacks (92.4\%) while maintaining strong performance on background removal (95.6\%). We release our benchmark to facilitate research into avatar-specific watermarking.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Face ReconstructionSimilar Papers 제목 키워드 기반
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embeddin…
Benchmarkingtext-to-speechText to SpeechFrom Attack to Protection: Leveraging Watermarking Attack Network for Advanced Add-on Watermarking
Multi-bit watermarking (MW) has been designed to enhance resistance against watermarking attacks, such as signal processing operations and geometric distortions. Various benchmark tools exist to assess this robustness th…
BenchmarkingVideoMarkBench: Benchmarking Robustness of Video Watermarking
The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has be…
BenchmarkingVedicTHG: Symbolic Vedic Computation for Low-Resource Talking-Head Generation in Educational Avatars
Talking-head avatars are increasingly adopted in educational technology to deliver content with social presence and improved engagement. However, many recent talking-head generation (THG) methods rely on GPU-centric neur…
WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models
To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to t…
BenchmarkingInstruction Following