John Klein
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
John Klein has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Olivier Colot
University of Mons
10 shared publications - Sébastien Destercke
Université de Technologie de Compiègne
4 shared publications - Solene Bernard
CNRS, Centrale Lille, UMR 9189 CRIStAL, Univ. Lille, Lille, France
3 shared publications - Tomáš Pevný
Faculty of Electrical Engineering, Czech Technical University, Prague, Czech Republic
3 shared publications - Benjamin Guedj
Department of Computer Science University College London
2 shared publications Christele Lecomte
University and INSA of Rouen, LITIS EA 4108, BP 12 - 76801 St Etienne du Rouvray, France
2 shared publications
Latest Publications
- 22 December 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 152, 106454
Self-mentoring: A new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation
- 22 December 2022
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 152, 106454
Self-mentoring: A new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation
- Open Access
- 14 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 3539-3554
Backpack: A Backpropagable Adversarial Embedding Scheme
A min max protocol offers a general method to automatically optimize steganographic algorithm against a wide class of steganalytic detectors. The quality of the resulting steganograhic algorithm depends on the ability to find an “adversarial” stego image undetectable by a set of detectors while communicating a given message. Despite min max protocol instantiated with ADV-EMB scheme leading to unexpectedly good results, we show it suffers a significant flaw and we present a theoretically sound solution called Backpack. Extensive experimental verification of min max protocol with Backpack shows superior performance to ADV-EMB, the generality of the tool by targeting a new JPEG QF100 compatibility attack and further improves the security of steganographic algorithms.
- 14 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 3539-3554
Open AccessBackpack: A Backpropagable Adversarial Embedding Scheme
A min max protocol offers a general method to automatically optimize steganographic algorithm against a wide class of steganalytic detectors. The quality of the resulting steganograhic algorithm depends on the ability to find an “adversarial” stego image undetectable by a set of detectors while communicating a given message. Despite min max protocol instantiated with ADV-EMB scheme leading to unexpectedly good results, we show it suffers a significant flaw and we present a theoretically sound solution called Backpack. Extensive experimental verification of min max protocol with Backpack shows superior performance to ADV-EMB, the generality of the tool by targeting a new JPEG QF100 compatibility attack and further improves the security of steganographic algorithms.
- 4 August 2022
- Published by Elsevier in Signal Processing
- Vol. 201
State space partitioning based on constrained spectral clustering for block particle filtering
- 4 August 2022
- Published by Elsevier in Signal Processing
- Vol. 201
State space partitioning based on constrained spectral clustering for block particle filtering
- Open Access
- 17 June 2021
- Published by Association for Computing Machinery (ACM)
- p. 105-112
Optimizing Additive Approximations of Non-additive Distortion Functions
The progress in steganography is hampered by a gap between non-additive distortion functions, which capture well complex dependencies in natural images, and their additive counterparts, which are efficient for data embedding. This paper proposes a theoretically justified method to approximate the former by the latter. The proposed method, called Backpack (for BACKPropagable AttaCK), combines new results in the approximation of gradients of discrete distributions with a gradient of implicit functions in order to derive a gradient w.r.t. the distortion of each JPEG coefficient. Backpack combined with the min max iterative protocol leads to a very secure steganographic algorithm. For example, the error rate of XuNet on 512 X 512 JPEG images, compressed with quality factor 100 and a payload of 0.4 bits per non-zero AC coefficient is 37.3% with Backpack, compared to a 26.5% error rate using ADV-EMB with minmax (considered state of the art in this work) and a 16.9% error rate with J-UNIWARD.
- 17 June 2021
- Published by Association for Computing Machinery (ACM)
- p. 105-112
Open AccessOptimizing Additive Approximations of Non-additive Distortion Functions
The progress in steganography is hampered by a gap between non-additive distortion functions, which capture well complex dependencies in natural images, and their additive counterparts, which are efficient for data embedding. This paper proposes a theoretically justified method to approximate the former by the latter. The proposed method, called Backpack (for BACKPropagable AttaCK), combines new results in the approximation of gradients of discrete distributions with a gradient of implicit functions in order to derive a gradient w.r.t. the distortion of each JPEG coefficient. Backpack combined with the min max iterative protocol leads to a very secure steganographic algorithm. For example, the error rate of XuNet on 512 X 512 JPEG images, compressed with quality factor 100 and a payload of 0.4 bits per non-zero AC coefficient is 37.3% with Backpack, compared to a 26.5% error rate using ADV-EMB with minmax (considered state of the art in this work) and a 16.9% error rate with J-UNIWARD.
- 4 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 16 (15566013) , 812-823
Explicit Optimization of min max Steganographic Game
This paper proposes an algorithm which allows Alice to simulate the game played between her and Eve. Under the condition that the set of detectors that Alice assumes Eve to have is sufficiently rich (e.g. CNNs), and that she has an algorithm enabling to avoid detection by a single classifier (e.g adversarial embedding, gibbs sampler, dynamic STCs), the proposed algorithm converges to an efficient steganographic algorithm. This is possible by using a min max strategy which consists at each iteration in selecting the least detectable stego image for the best classifier among the set of Eve’s learned classifiers. The algorithm is extensively evaluated and compared to prior arts and results show the potential to increase the practical security of classical steganographic methods. For example the error probability Perr of XU-Net on detecting stego images with payload of 0.4 bpnzAC embedded by J-Uniward and QF 75 starts at 7.1% and is increased by +13.6% to reach 20.7% after eight iterations. For the same embedding rate and for QF 95, undetectability by XU-Net with J-Uniward embedding is 23.4%, and it jumps by +25.8% to reach 49.2% at iteration 3.
- 4 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 16 (15566013) , 812-823
Explicit Optimization of min max Steganographic Game
This paper proposes an algorithm which allows Alice to simulate the game played between her and Eve. Under the condition that the set of detectors that Alice assumes Eve to have is sufficiently rich (e.g. CNNs), and that she has an algorithm enabling to avoid detection by a single classifier (e.g adversarial embedding, gibbs sampler, dynamic STCs), the proposed algorithm converges to an efficient steganographic algorithm. This is possible by using a min max strategy which consists at each iteration in selecting the least detectable stego image for the best classifier among the set of Eve’s learned classifiers. The algorithm is extensively evaluated and compared to prior arts and results show the potential to increase the practical security of classical steganographic methods. For example the error probability Perr of XU-Net on detecting stego images with payload of 0.4 bpnzAC embedded by J-Uniward and QF 75 starts at 7.1% and is increased by +13.6% to reach 20.7% after eight iterations. For the same embedding rate and for QF 95, undetectability by XU-Net with J-Uniward embedding is 23.4%, and it jumps by +25.8% to reach 49.2% at iteration 3.
- 1 July 2020
- Published by Elsevier in Expert Systems with Applications
- Vol. 150
SPOCC: Scalable POssibilistic Classifier Combination - toward robust aggregation of classifiers
- 1 July 2020
- Published by Elsevier in Expert Systems with Applications
- Vol. 150
SPOCC: Scalable POssibilistic Classifier Combination - toward robust aggregation of classifiers
- 1 April 2020
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 65 (7) , 075002
MR to CT synthesis with multicenter data in the pelvic area using a conditional generative adversarial network
The establishment of an MRI-only workflow in radiotherapy depends on the ability to generate an accurate synthetic CT (sCT) for dose calculation. Previously proposed methods have used a Generative Adversarial Network (GAN) for fast sCT generation in order to simplify the clinical workflow and reduces uncertainties. In the current paper we use a conditional Generative Adversarial Network (cGAN) framework called pix2pixHD to create a robust model prone to multicenter data. This study included T2-weighted MR and CT images of 19 patients in treatment position from 3 different sites. The cGAN was trained on 2D transverse slices of 11 patients from 2 different sites. Once trained, the network was used to generate sCT images of 8 patients coming from a third site. The Mean Absolute Errors (MAE) for each patient were evaluated between real and synthetic CTs. A radiotherapy plan was optimized on the sCT series and re-calculated on CTs to assess the dose distribution in terms of voxel-wise dose difference and Dose Volume Histograms (DVH) analysis. It takes on average of 7.5 s to generate a complete sCT (88 slices) for a patient on our GPU. The average MAE in HU between the sCT and actual patient CT (within the body contour) is 48.5 ± 6 HU with our method. The maximum dose difference to the target is 1.3%. This study demonstrates that an sCT can be generated in a multicentric context, with fewer pre-processing steps while being fast and accurate.
- 1 April 2020
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 65 (7) , 075002
MR to CT synthesis with multicenter data in the pelvic area using a conditional generative adversarial network
The establishment of an MRI-only workflow in radiotherapy depends on the ability to generate an accurate synthetic CT (sCT) for dose calculation. Previously proposed methods have used a Generative Adversarial Network (GAN) for fast sCT generation in order to simplify the clinical workflow and reduces uncertainties. In the current paper we use a conditional Generative Adversarial Network (cGAN) framework called pix2pixHD to create a robust model prone to multicenter data. This study included T2-weighted MR and CT images of 19 patients in treatment position from 3 different sites. The cGAN was trained on 2D transverse slices of 11 patients from 2 different sites. Once trained, the network was used to generate sCT images of 8 patients coming from a third site. The Mean Absolute Errors (MAE) for each patient were evaluated between real and synthetic CTs. A radiotherapy plan was optimized on the sCT series and re-calculated on CTs to assess the dose distribution in terms of voxel-wise dose difference and Dose Volume Histograms (DVH) analysis. It takes on average of 7.5 s to generate a complete sCT (88 slices) for a patient on our GPU. The average MAE in HU between the sCT and actual patient CT (within the body contour) is 48.5 ± 6 HU with our method. The maximum dose difference to the target is 1.3%. This study demonstrates that an sCT can be generated in a multicentric context, with fewer pre-processing steps while being fast and accurate.
- 28 March 2020
- Published by Springer Nature
- p. 301-316
Decentralized Learning with Budgeted Network Load Using Gaussian Copulas and Classifier Ensembles
- 28 March 2020
- Published by Springer Nature
- p. 301-316
Decentralized Learning with Budgeted Network Load Using Gaussian Copulas and Classifier Ensembles
- Open Access
SPOCC: Scalable POssibilistic Classifier Combination -- toward robust aggregation of classifiers
We investigate a problem in which each member of a group of learners is trained separately to solve the same classification task. Each learner has access to a training dataset (possibly with overlap across learners) but each trained classifier can be evaluated on a validation dataset. We propose a new approach to aggregate the learner predictions in the possibility theory framework. For each classifier prediction, we build a possibility distribution assessing how likely the classifier prediction is correct using frequentist probabilities estimated on the validation set. The possibility distributions are aggregated using an adaptive t-norm that can accommodate dependency and poor accuracy of the classifier predictions. We prove that the proposed approach possesses a number of desirable classifier combination robustness properties.
Open AccessSPOCC: Scalable POssibilistic Classifier Combination -- toward robust aggregation of classifiers
We investigate a problem in which each member of a group of learners is trained separately to solve the same classification task. Each learner has access to a training dataset (possibly with overlap across learners) but each trained classifier can be evaluated on a validation dataset. We propose a new approach to aggregate the learner predictions in the possibility theory framework. For each classifier prediction, we build a possibility distribution assessing how likely the classifier prediction is correct using frequentist probabilities estimated on the validation set. The possibility distributions are aggregated using an adaptive t-norm that can accommodate dependency and poor accuracy of the classifier predictions. We prove that the proposed approach possesses a number of desirable classifier combination robustness properties.
- 23 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 68 (12) , 11420-11426
Impact of the Velocity Profile on Energy Consumption of Electric Vehicles
- 23 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 68 (12) , 11420-11426
Impact of the Velocity Profile on Energy Consumption of Electric Vehicles