This work introduces RemTraceNet, which fuses constrained residuals, local relations, FFT/Haar statistics, and block-DCT evidence at native resolution and outperforms retrained SRNet, ZhuNet, and SiaStegNet baselines by 10.80--15.68 percentage points.
Abstract
Removing an invisible watermark and concealing the forensic evidence are distinct objectives: successfully disrupting the embedded watermark does not imply that the removal process is forensically undetectable. When verification fails, removal traces can provide complementary evidence for provenance and ownership verification, whereas their absence leaves the cause of the failure ambiguous. Existing methods are typically evaluated by watermark suppression and perceptual quality, while forensic stealth is rarely considered. We therefore study watermark-attack-specific few-shot forensics: for each known pipeline, a specialist can separate its outputs from paired clean and unattacked watermarked controls. Separate Attack-vs-Clean and Attack-vs-Watermarked evaluations prevent watermark-presence shortcuts. Image-aligned and prompt-matched controls are used for post-hoc and generator-integrated schemes, respectively. In this work, we introduce RemTraceNet, which fuses constrained residuals, local relations, FFT/Haar statistics, and block-DCT evidence at native resolution. Across 23 removal pipelines and 10 watermark configurations, we evaluate native 256 x 256 and 512 x 512 inputs. With 100 attacked training images per pipeline, the three-seed TPR@1%FPR, macro-averaged over attacks and watermark configurations, ranges from 82.75% to 88.17% across resolutions and control types. Under the condition of same labels and protocol, RemTraceNet outperforms retrained SRNet, ZhuNet, and SiaStegNet baselines by 10.80--15.68 percentage points. Extensive experimental results show that erasing a watermark and erasing evidence of its removal are distinct challenges, and that removal traces remain learnable under limited supervision.
Disentangle and Drop (DnD) is proposed, an attack that is agnostic to the watermark method and treats watermark removal as a representation routing problem and shows that one shared operating setting gives competitive removal with high visual fidelity.
Qi Li, Ji-Dong Yang, Feng-Lei Fan et al.· arXiv.org· 0 citations
This work identifies two complementary laundering regimes: OpenAI models produce the strongest payload disruption across the evaluated schemes, whereas Nano Banana 2 shows that DwtDct remains vulnerable under high-fidelity reconstruction.
Neural audio watermarks are increasingly used to attribute and detect AI-generated speech, so their practical value rests on how cheaply an adversary can remove them. Robustness is usually measured by running a fixed battery of distortions blindly against every scheme. We instead make removal diagnostic: from a few cle...
Results show that apparent attack winners depend on text-quality constraints, attack generality, and capability assumptions, and that apparent attack winners depend on text-quality constraints, attack generality, and capability assumptions.
Kai-Rong Li, Zhi-Kun Zhang, Xiao-Nan Ren et al.· 1 citation
Invisible image watermark removal has received growing attention. Despite substantial progress, existing attacks face a tension between practicality and specificity. Attacks exploiting detector outputs, decoder responses, or paired images can be tailored to the watermark decision boundary, but require information rarel...
Jun Yao, Chao Wang, Yu-Peng Qiu et al.· 0 citations
Audio watermarking protects digital speech by embedding imperceptible signals for ownership verification and misuse tracing. However, the security of learning-based watermarking remains insufficiently understood under realistic adversarial removal, where attackers cannot access or query the watermark encoder, decoder,...