In this paper, we study the possibility to feed machine learning models with JPEG compressed images during their training phase. The underlying objective is to evaluate if JPEG decompression can be avoided so as to gain in computation time and, if yes, at what price in terms of model accuracy. To do so, we trained two well-known machine learning models: Neural Networks (NN) and Convolutional Neural Network (CNN), with pieces of data issued from different steps of the partial JPEG decompression of images. We analyze how such partially decompressed JPEG data influence machine learning model accuracy. We also study the impact of the JPEG quality factor. Experiments conducted on two image databases, MNIST database and CIFAR-10 database, show that the learning task complexity of NN models can be reduced working with partially decompressed images with a low model accuracy loss, while for CNN model's accuracy loss depends on the JPEG data. A trade-off has to be found. With a quality factor of 80, the decompression computation complexity gain is of 45% for an accuracy loss of 13%. This work also point out the need for model adapted to compressed data.

In this paper, we propose the first joint watermarking-encryption-compression scheme for the purpose of protecting of medical images. The main originality of this scheme stands on its ability to give access to watermarking-based security services from both encrypted and compressed image bitstreams without having to decrypt or to decompress them, even partially. More clearly, there is no need neither to decrypt the encrypted image bitstream nor to decode the compressed image bitstream in order to extract watermarks. A second contribution is that it combines in a single algorithm the bit substitution watermarking modulation with JPEG-LS and the AES block cipher algorithm in its CBC mode. On their side, decompression, decryption and message extraction are conducted separately. Doing so makes our scheme compliant to the medical image standard DICOM. This scheme allows tracing images and controlling their reliability (i.e. based on proofs of image integrity and authenticity) either from the encrypted domain or from the compressed one. Experiments conducted on broad sets of Retina and ultrasound medical images demonstrate the capability of our system to securely make available a message in both encrypted and compressed domains while minimizing image distortion. Achieved watermarking capacities are large enough to support several watermarking-based security services at the same time.

In this paper, we propose the first joint watermarking-encryption-compression scheme for the protection of medical images. Its originality is twofold. In a first time, it allows the access to watermarking-based security services from the encrypted and the compressed bitstreams without having to parse them even partially. It becomes possible to trace images and control their reliability (i.e. integrity and authenticity) from both the encrypted and compressed domains. In a second, it stands on the combination of bit-substitution watermarking, JPEG-LS and the AES block cipher in its CBC mode so as to make our scheme compliant with DICOM. Experiments conducted on different medical images modalities (radiographic and retina images) demonstrate the capability of our system to securely make available a message in both encrypted and compressed domains while minimizing the distortion of the image.

In this paper, we propose an homomorphic proxy re-encryption scheme (HPRE) that allows different users to share data they outsourced homomorphically encrypted using their respective public keys with the possibility by next to process such data remotely. Its originality stands on a solution we propose so as to compute the difference of data encrypted with Damgard-Jurik cryptosystem. It takes also advantage of a secure combined linear congruential generator that we implemented in the Damgard-Jurik encrypted domain. Basically, in our HPRE scheme, the two users, the delegator and the delegate, ask the cloud server to generate an encrypted noise based on a secret key, both users previously agreed on. Based on our solution to compute the difference in Damgard-Jurik encrypted domain, the cloud computes in clear the differences in-between the encrypted noise and the encrypted data of the delegator, obtaining thus blinded data. In order the delegate gets access to the data, the cloud just has to encrypt these differences using the delegate's public key and then removes the noise. This solution doesn't need extra communication between the cloud and the delegator. Our HPRE was implemented in the case of the sharing of uncompressed images stored in the cloud showing good time computation performance, it is unidirectional and collusion-resistant. Nevertheless, it is not limited to images and can be used with any kinds of data.

This paper describes a computer-aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has proven useful for medical decision support in previous works from our team. In the proposed framework, breasts are first partitioned adaptively into regions. Then, features derived from the detection of lesions (masses and microcalcifications) as well as textural features, are extracted from each region and combined in order to classify mammography examinations as "normal" or "abnormal". Whenever an abnormal examination record is detected, the regions that induced that automated diagnosis can be highlighted. Two strategies are evaluated to define this anomaly detector. In a first scenario, manual segmentations of lesions are used to train an SVM that assigns an anomaly index to each region; local anomaly indices are then combined into a global anomaly index. In a second scenario, the local and global anomaly detectors are trained simultaneously, without manual segmentations, using various MIL algorithms (DD, APR, mi-SVM, MI-SVM and MILBoost). Experiments on the DDSM dataset show that the second approach, which is only weakly-supervised, surprisingly outperforms the first approach, even though it is strongly-supervised. This suggests that anomaly detectors can be advantageously trained on large medical image archives, without the need for manual segmentation.

In case of litigation in telemedicine applications, one main issue is to determine liabilities of each physician involved in the data exchange. To achieve this goal, we propose an efficient watermarking based telemedicine protocol. Its objective is not only to ensure the security of data but also to provide evidence that an exchange took place. We show how watermarking in combination with cryptographic mechanisms and a third party can enforce data and exchange traceability. The efficiency of our solution is demonstrated by means of a security analysis.

In this paper, we propose a joint encryption/water-marking system for the purpose of protecting medical images. This system is based on an approach which combines a substitutive watermarking algorithm, the quantization index modulation, with an encryption algorithm: a stream cipher algorithm (e.g., the RC4) or a block cipher algorithm (e.g., the AES in cipher block chaining (CBC) mode of operation). Our objective is to give access to the outcomes of the image integrity and of its origin even though the image is stored encrypted. If watermarking and encryption are conducted jointly at the protection stage, watermark extraction and decryption can be applied independently. The security analysis of our scheme and experimental results achieved on 8-bit depth ultrasound images as well as on 16-bit encoded positron emission tomography images demonstrate the capability of our system to securely make available security attributes in both spatial and encrypted domains while minimizing image distortion. Furthermore, by making use of the AES block cipher in CBC mode, the proposed system is compliant with or transparent to the DICOM standard.