Sorry, you need to enable JavaScript to visit this website.

Lecture notes for undergraduate and first-year graduate students on digital watermarking and data embedding in multimedia data.

Based on lectures developed at University of Maryland, College Park, USA.


Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a solution for model attribution, i.e., the classification of synthetic contents by their source models via watermarks embedded in the contents.


Steganography comprises the mechanics of hiding data in a host media that may be publicly available. While previous works focused on unimodal setups (e.g., hiding images in images, or hiding audio in audio), PixInWav targets the multimodal case of hiding images in audio. To this end, we propose a novel residual architecture operating on top of short-time discrete cosine transform (STDCT) audio spectrograms. Among our results, we find that the residual steganography setup we propose allows an encoding of the hidden image that is independent from the host audio without compromising quality.


Deep neural network (DNN) watermarking is one of the main techniques to protect the DNN. Although various DNN watermarking schemes have been proposed, none of them is able to resist the DNN encryption. In this paper, we propose an encryption resistent DNN watermarking scheme, which is able to resist the parameter shuffling based DNN encryption. Unlike the existing schemes which use the kernels separately for watermarking embedding, we propose to embed the watermark into the fused kernels to resist the parameter shuffling.


Today, 3D objects are an increasingly popular form of media. It has become necessary to secure them during their transmission or archiving. In this paper, we propose a two tier reversible data hiding method for 3D objects in the encrypted domain. Based on the homomorphic properties of the Paillier cryptosystem, our proposed method embeds a first tier message in the encrypted domain which can be extracted in either the encrypted domain or the clear domain. Indeed, our method produces a marked 3D object which is visually very similar to the original object.


Nowadays a steganography has to face challenges to both feature-based staganalysis and convolutional neural network (CNN) based steganalysis. In this paper, we present a novel steganographic scheme to incorporate synchronizing modification directions and iterative adversarial perturbations to enhance steganographic performance. Firstly an existing steganographic function is employed to compute initial costs. Then the secret message bits are embedded following clustering modification directions profile.


Unlike most existing steganography methods which are main- ly focused on designing embedding cost, in this paper, we propose a new method to enhance existing steganographic methods via stego generation and selection. The proposed method firstly trains a steganalytic network according to the steganography to be enhanced, and then tries to adjust a tiny part of original embedding costs based on the magnitudes of it and the corresponding gradients obtained from the pre-trained network, and generates many candidate stegos in a random manner.