Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging
Authors: Chaoning Zhang, Philipp Benz, Adil Karjauv, Geng Sun, In So Kweon
NeurIPS 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform extensive analysis and demonstrate that the success of deep steganography can be attributed to a frequency discrepancy between C and the encoded secret image. Despite S being hidden in a cover-agnostic manner, strikingly, UDH achieves a performance comparable to the existing DDH. ... We co-train H and R on the Image Net [13] training dataset with the ADAM optimizer [31]. The APD (average pixel discrepancy) performance evaluated on the Image Net validation dataset is available in Table 1. |
| Researcher Affiliation | Academia | Chaoning Zhang KAIST EMAIL Philipp Benz KAIST EMAIL Adil Karjauv KAIST EMAIL Geng Sun KAIST EMAIL In So Kweon KAIST EMAIL |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code: https://github.com/Chaoning Zhang/Universal-Deep-Hiding |
| Open Datasets | Yes | We co-train H and R on the Image Net [13] training dataset with the ADAM optimizer [31]. |
| Dataset Splits | Yes | The APD (average pixel discrepancy) performance evaluated on the Image Net validation dataset is available in Table 1. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments. It mentions using 'DNN-based' methods but no hardware specifications. |
| Software Dependencies | No | The paper mentions using the 'ADAM optimizer' and 'U-Net from Cycle-GAN' but does not specify their version numbers or any other software dependencies with version details. |
| Experiment Setup | Yes | The optimization goal is to minimize the loss defined as L(S, Se, S ) = ||Se|| + β||S S||, where Se = C C and following [2] we set β to 0.75. ... The image resolution size is set to 128 128. |