FiLM-CAM: Keyed Feature Modulation for Conditional-Access Watermarking

Researchers posted arXiv paper 2610.30347v1 introducing FiLM-CAM, a conditional-access image watermarking method that uses a secret key to condition a Feature-wise Linear Modulation (FiLM) mechanism on the watermark signal's internal representation before embedding, coupling the payload to the key at the feature level rather than the pixel level. The decoder only recovers the payload when the same key is presented, and the system is trained to maximize the performance gap between authorized and unauthorized use, while the encoder estimates a watermark residual invariant to pre-existing watermarks to enable keyed removal via re-encoding, subtraction and iterative refinement. The authors report the approach works across multiple watermarking encoder-decoder backbones, positioning keyed feature modulation as an architecture-agnostic conditional access module for image watermarking.

arXiv:2610.30347v1 Announce Type: new Abstract: We propose FiLM-CAM; a conditional-access image watermarking approach that enforces authorized encoding, decoding, and removal through keyed feature modulation. A secret key conditions a Feature-wise Linear Modulation FiLM mechanism that transforms the internal representation of the watermark signal before embedding, thereby coupling the payload to the key at the feature, rather than pixel level. The same key must be presented to condition the decoder to correctly recover the payload embedded in an image. To enforce conditional access, we train the system to maximize the performance gap between authorized and unauthorized use, ensuring reliable extraction under the correct key while inducing failure under incorrect keys. In addition, we design our encoder to estimate the watermark residual invariant to the presence of pre-existing watermarks. This design enables conditional watermark removal via simple re-encoding and subtraction of the residual using iterative refinement, contingent on knowledge of the secret key. We evaluate FiLM-CAM across multiple watermarking encoder-decoder backbones, demonstrating that keyed feature modulation serves as an effective, architecture-agnostic conditional access module CAM for image watermarking.