Publications

2023

• Tailored vertex ordering for faster triangle listing in large graphs
  
  • Lécuyer Fabrice
  • Jachiet Louis
  • Magnien Clémence
  • Tabourier Lionel
  , 2023. Listing triangles is a fundamental graph problem with many applications, and large graphs require fast algorithms. Vertex ordering allows the orientation of edges from lower to higher vertex indices, and state-of-the-art triangle listing algorithms use this to accelerate their execution and to bound their time complexity. Yet, only basic orderings have been tested. In this paper, we show that studying the precise cost of algorithms instead of their bounded complexity leads to faster solutions. We introduce cost functions that link ordering properties with the running time of a given algorithm. We prove that their minimization is NP-hard and propose heuristics to obtain new orderings with different trade-offs between cost reduction and ordering time. Using datasets with up to two billion edges, we show that our heuristics accelerate the listing of triangles by an average of 38% when the ordering is already given as an input, and 16% when the ordering time is included. (10.1137/1.9781611977561.ch7)
  DOI : 10.1137/1.9781611977561.ch7
• Reconfigurable Adaptive Channel Sensing
  
  • Mukherjee Manuj
  • Tchamkerten Aslan
  • Jabbour Chadi
  IEEE Transactions on Green Communications and Networking, IEEE, 2023, 7 (3), pp.1394 - 1406. This paper proposes an energy-efficient detection scheme, referred to as AdaSense, that is particularly suitable in the sparse regime when events to be detected happen rarely. To minimize energy consumption, AdaSense exploits the dependency between the receiver noise figure (i.e., the receiver added noise) and the receiver power consumption; less noisy channel observations typically imply higher power consumption. AdaSense is duty-cycled and begins each cycle with a few channel observations in a low-power-low-reliability mode. Based on these observations, it makes a first tentative decision on whether or not a message is present. If no message is declared, AdaSense waits till the beginning of the next cycle and starts afresh. If a message is tentatively declared, AdaSense enters a confirmation second phase, takes more samples, but now in a high-power-high-reliability mode. If these observations confirm the tentative decision, AdaSense stops, else AdaSense waits till the beginning of the next cycle and starts afresh in the low-power-low-reliability mode. Compared to prominent detection schemes such as the clear channel assessment algorithm of the Berkeley Media Access Control (BMAC) protocol, AdaSense provides relative energy gains that grow unbounded in the small probability of false-alarm regime, as communication gets sparser. In the non-asymptotic regime, energy gains are 30% to 75% for communication scenarios typically found in the context of wake-up receivers. (10.1109/TGCN.2023.3238176)
  DOI : 10.1109/TGCN.2023.3238176
• Multi-temporal speckle reduction with self-supervised deep neural networks
  
  • Meraoumia Inès
  • Dalsasso Emanuele
  • Denis Loïc
  • Abergel Rémy
  • Tupin Florence
  IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers, 2023, 61. Speckle filtering is generally a prerequisite to the analysis of synthetic aperture radar (SAR) images. Tremendous progress has been achieved in the domain of single-image despeckling. Latest techniques rely on deep neural networks to restore the various structures and textures peculiar to SAR images. The availability of time series of SAR images offers the possibility of improving speckle filtering by combining different speckle realizations over the same area. The supervised training of deep neural networks requires ground-truth speckle-free images. Such images can only be obtained indirectly through some form of averaging, by spatial or temporal integration, and are imperfect. Given the potential of very high quality restoration reachable by multi-temporal speckle filtering, the limitations of ground-truth images need to be circumvented. We extend a recent self-supervised training strategy for single-look complex SAR images, called MERLIN, to the case of multi-temporal filtering. This requires modeling the sources of statistical dependencies in the spatial and temporal dimensions as well as between the real and imaginary components of the complex amplitudes. Quantitative analysis on datasets with simulated speckle indicates a clear improvement of speckle reduction when additional SAR images are included. Our method is then applied to stacks of TerraSAR-X images and shown to outperform competing multitemporal speckle filtering approaches. The code of the trained models and supplementary results are made freely available at https://gitlab.telecom-paris.fr/ring/ multi-temporal-merlin/. (10.1109/TGRS.2023.3237466)
  DOI : 10.1109/TGRS.2023.3237466
• Design Optimization of 12-Core Amplifier based on Erbium Ytterbium Co-doped Fiber for Spatial Multiplexed Transmission System
  
  • Lebreton Aurelien
  • Melin Gilles
  • Bordais Sylvain
  • Kerampran Romain
  • Pincemin Erwan
  • Taunay Thierry
  • Jauffrit Jeremie
  • Disez Pierre-Yves
  • Le Bouette Claude
  • Jaouen Yves
  • Morvan Michel
  • Lu Chao
  Journal of Lightwave Technology, Institute of Electrical and Electronics Engineers (IEEE)/Optical Society of America(OSA), 2023, 41 (02), pp.462 - 476. A 20 dB gain 12 cores Er 3+ /Yb 3+ co-doped cladding pumped amplifier in C-band with only 5.3 W of pump power has been achieved. A classical rate equation model has been applied for the amplifier design. Parameters such as active fiber length, pump power and ions concentration have been investigated and optimized. Results obtained through numerical simulation and experimental investigations are compared. Different use cases of MC-EYDFA have been studied, such as various transmission configuration or multi-core amplifier in ROADM architectures. 1200-km with 200G DP-QPSK and 300 km with 400G DP-16QAM are achieved in serial configuration at 1550 nm. This is a first step towards SDM transmission using power efficient amplifiers, for cost, energy and footprint saving. (10.1109/JLT.2022.3217308)
  DOI : 10.1109/JLT.2022.3217308
• Iiro Honkala’s contributions to some conjectures on identifying codes
  
  • Hudry Olivier
  , 2023.
• AI models for digital signal processing in future 6G-IoT networks
  
  • Larue Guillaume
  , 2023. Wireless technologies are of paramount importance to today's societies and future 6th generation communication networks are expected to address many societal and technological challenges. While communications infrastructures have a growing environmental impact that needs to be reduced, digital technologies also have a role to play in reducing the impact of all sectors of the economy. To this end, the future networks will not only have to enable more efficient information transfer, but also meet the growing need for data exchange capacity. This is particularly the role of the Internet of Things use cases, where a massive number of sensors allow to monitor complex systems. These use cases are associated with many constraints such as limited energy resources and complexity. Therefore, an efficient and low-complexity physical layer - responsible for the transmission of information between the network nodes - is absolutely crucial. In this regard, the use of artificial intelligence techniques is relevant. On the one hand, the mathematical framework of neural networks allows for efficient and low-cost generic hardware implementations. On the other hand, the application of learning procedures can improve the performance of certain algorithms. In this work, we are interested in the use of neural networks and machine learning for digital signal processing in the context of 6G-IoT networks. First, we are interested in the transcription of certain equalisation, demodulation and decoding algorithms from the digital communications literature into neural networks. Secondly, we are interested in the application of learning mechanisms on these neural network structures in order to improve their performance. A linear block decoder is proposed which allows the blind discovery of a decoding scheme whose performance is at least equivalent to that of the reference decoder. Finally, an end-to-end structure is presented, allowing joint learning of an encoding/decoding scheme with performance and complexity comparable to state-of-the-art solutions. (10.70675/b70858e5z6800z430dza632z33528def55bb)
  DOI : 10.70675/b70858e5z6800z430dza632z33528def55bb
• Function-valued regression with kernels : Improving speed, flexibility and robustness
  
  • Bouche Dimitri
  , 2023. With the increasing ubiquity of data-collecting devices, a great variety of phenomena is monitored with finer and finer accuracy, which constantly expands the scope of Machine Learning applications. Dealing with such volume of data efficiently is however challenging. Fortunately, as measurements get denser, they may become gradually redundant. We can then greatly reduce the burden by finding a representation which exploits properties of the generating process and/or is tailored for the application at hand.This thesis revolves around an aspect of this idea: functional data. Data indeed consist of discrete measurements, but sometimes thinking of those as functional, we can exploit prior knowledge on smoothness to obtain a better yet lower dimensional representation. The focus is on nonlinear models for functional output regression (FOR), relying on an extension of reproducing kernel Hilbert spaces for vector-valued functions (vv-RKHS), which is the cornerstone of many nonlinear existing FOR methods. We propose to challenge those in two aspects: their computational complexity with respect to the number of measurements per function and their focusing solely on the square loss.To that end, we introduce the new framework of kernel projection learning (KPL) combining vv-RKHSs and representation of signals in dictionaries. The loss remains functional, however the model predicts only a finite number of representation coefficients. This approach retains the many advantages of vv-RKHSs yet greatly alleviates the computational burden incurred by the functional outputs. We derive two estimators in closed-form using the square loss, one for fully observed functions and one for discretized ones. We show that both are consistent in terms of excess risk. We demonstrate as well the possibility to use other differentiable and convex losses, to combine this framework with large scale kernel methods and to automatically select the dictionary using a structured penalty.In another contribution, we propose to solve the regression problem in vv-RKHSs of function-valued functions for the family of convoluted losses which we introduce. Those losses can either promote sparsity or robustness with a parameter controlling the degree of locality of those properties. Thanks to their structure, they are particularly amenable to dual approaches which we investigate. We then overcome the challenges posed by the functional nature of the dual variables by proposing two possible representations and we propose corresponding algorithms. (10.70675/4ef05483z196dz4df8z8794z240f95694566)
  DOI : 10.70675/4ef05483z196dz4df8z8794z240f95694566
• Demonstration Of Performance For Low Cost Personal HSM
  
  • Urien Pascal
  , 2023, pp.879-880. This demonstration presents an original personal Hardware Secure Module (HSM) server, built from grid of secure elements and host system (Raspberry Pi), with internet connectivity. Each secure element is plugged in a board with a microcontroller providing I2C (Inter-Integrated Circuit) interface. The host system executes the open software IoSEv5 (Internet of Secure Elements version 5), which manages two T CP/IP daemons. First is used for downloading software in secure elements, second is a TLS front server that send/receive TLS packets to/from TLS backend servers running in secure elements. Applications hosted in secure elements implement a keystore, which stores cryptographic keys and computes signature over 256 bits elliptic curve. The demonstration shows the grid at work with 16 simultaneous TLS sessions performing signature operation. It shows that performance follows the Amdahl's law, with a speeding factor of about 50. (10.1109/CCNC51644.2023.10060586)
  DOI : 10.1109/CCNC51644.2023.10060586
• Towards a centralized security architecture for SOME/IP automotive services
  
  • Khemissa Hamza
  • Urien Pascal
  , 2023, pp.977-978. Connected and autonomous vehicles (CAVs) consist of a number of networked computer components, called Electronic Control Units (ECUs). Scalable service-Oriented MiddlewarE over IP (SOME/IP) is a communication middleware standardized used to exchange various services between disjoint applications on distinct ECUs. However, it presents lack of authentication and confidentiality features. In this paper, we propose a centralized security architecture for SOME/IP automotive services. First, we present a lightweight symmetric cryptography based session key agreement scheme between each ECU and the manufacturer data center, which uses a random nonce, concatenation operator, a simple hash function and a keyedhash message authentication code (HMAC). Then, we define the security parameters between the different ECUs for the invehicle Ethernet-based communications. We propose the use of DTLS using pre-shared keys (DTLS-PSK) in order to secure the transmission of SOME/IP messages, (10.1109/CCNC51644.2023.10059950)
  DOI : 10.1109/CCNC51644.2023.10059950
• Coalitional game-theoretical approach to coinvestment with application to edge computing
  
  • Patanè Rosario
  • Araldo Andrea
  • Chahed Tijani
  • Kiedanski Diego
  • Kofman Daniel
  , 2023, pp.517-522. We propose in this paper a coinvestment plan between several stakeholders of different types, namely a physical network owner, operating network nodes, e.g. a network operator or a tower company, and a set of service providers willing to use these resources to provide services as video streaming, augmented reality, autonomous driving assistance, etc. One such scenario is that of deployment of Edge Computing resources. Indeed, although the latter technology is ready, the high Capital Expenditure (CAPEX) cost of such resources is the barrier to its deployment. For this reason, a solid economical framework to guide the investment and the returns of the stakeholders is key to solve this issue. We formalize the coinvestment framework using coalitional game theory. We provide a solution to calculate how to divide the profits and costs among the stakeholders, taking into account their characteristics: traffic load, revenues, utility function. We prove that it is always possible to form the grand coalition composed of all the stakeholders, by showing that our game is convex. We derive the payoff of the stakeholders using the Shapley value concept, and elaborate on some properties of our game. We show our solution in simulation. (10.1109/CCNC51644.2023.10060093)
  DOI : 10.1109/CCNC51644.2023.10060093
• Public-attention-based Adversarial Attack on Traffic Sign Recognition
  
  • Chi Lijun
  • Msahli Mounira
  • Memmi Gerard
  • Qiu Han
  , 2023, pp.740-745. Autonomous driving systems (ADS) can instantaneously and accurately recognize traffic signs by using deep neural networks (DNNs). Although adversarial attacks are well-known to easily fool DNNs by adding tiny but malicious perturbations, most attack methods require sufficient information about the victim models (white-box) to perform. In this paper, we propose a black-box attack in the recognition system of ADS, Public Attention Attacks (PAA), that can attack a black-box model by collecting the generic attention patterns of other white-box DNNs to transfer the attack. Particularly, we select multiple dual or triple attention patterns of white-box model combinations to generate the transferable adversarial perturbations for PAA attacks. We perform the experimentation on four well-trained models in different adversarial settings separately. The results indicate that when more white-box models the adversary collects to perform PAA, the higher the attack success rate (ASR) he can achieve to attack the target black-box model. (10.1109/CCNC51644.2023.10060485)
  DOI : 10.1109/CCNC51644.2023.10060485
• Compressing Explicit Voxel Grid Representations: fast NeRFs become also small
  
  • Deng Chenxi Lola
  • Tartaglione Enzo
  , 2023, pp.1236-1245. (10.1109/WACV56688.2023.00129)
  DOI : 10.1109/WACV56688.2023.00129
• Fuzzy Sets Methods in Image Processing and Understanding
  
  • Bloch Isabelle
  • Ralescu Anca
  , 2023. (10.1007/978-3-031-19425-2)
  DOI : 10.1007/978-3-031-19425-2
• Solving stochastic weak Minty variational inequalities without increasing batch size
  
  • Pethick Thomas
  • Fercoq Olivier
  • Latafat Puya
  • Patrinos Panagiotis
  • Cevher Volkan
  , 2023. This paper introduces a family of stochastic extragradient-type algorithms for a class of nonconvex-nonconcave problems characterized by the weak Minty variational inequality (MVI). Unlike existing results on extragradient methods in the monotone setting, employing diminishing stepsizes is no longer possible in the weak MVI setting. This has led to approaches such as increasing batch sizes per iteration which can however be prohibitively expensive. In contrast, our proposed methods involves two stepsizes and only requires one additional oracle evaluation per iteration. We show that it is possible to keep one fixed stepsize while it is only the second stepsize that is taken to be diminishing, making it interesting even in the monotone setting. Almost sure convergence is established and we provide a unified analysis for this family of schemes which contains a nonlinear generalization of the celebrated primal dual hybrid gradient algorithm.
• A Consistent Diffusion-Based Algorithm for Semi-Supervised Graph Learning
  
  • Bonald Thomas
  • de Lara Nathan
  , 2023. The task of semi-supervised classification aims at assigning labels to all nodes of a graph based on the labels known for a few nodes, called the seeds. One of the most popular algorithms relies on the principle of heat diffusion, where the labels of the seeds are spread by thermoconductance and the temperature of each node at equilibrium is used as a score function for each label. In this paper, we prove that this algorithm is not consistent unless the temperatures of the nodes at equilibrium are centered before scoring. This crucial step does not only make the algorithm provably consistent on a block model but brings significant performance gains on real graphs.
• ADT: AI-Driven network Telemetry processing on routers
  
  • Foroughi Parisa
  • Brockners Frank
  • Rougier Jean-Louis
  Computer Networks, Elsevier, 2023, 220, pp.109474-1:109474-17. Network monitoring is a pivotal part of network management and operations. It is responsible for monitoring the behavior of the network to assure its functionality within expectation and to guarantee a smooth-running environment for enabling of various services. Therefore, operators are interested in gaining a comprehensive assessment of their network elements and tracking operational changes to facilitate timely correction of any deviation. Commonly, this assessment is achieved by performing regular manual checks of different operational counters and defining expert rules from known root causes. The common approach requires the maintenance of a regularly updated set of rules and only goes as far as the operator's pre-gained knowledge of the system. With the growing complexity of the networks as well as the availability of more data, a more efficient monitoring approach is necessary to address the emerging network monitoring requirements. In this paper, a novel unsupervised approach is proposed that is capable of exploring a broader set of counters (not limited to the handpicked Key Performance Indicators (KPIs)). The goal is to leverage the dependencies between the counters in order to discover complex state changes that might have otherwise slipped the operator's view. This paper proposes ADT, an AI-driven telemetry processing solution that facilitates monitoring of a larger set of counters. The Detector block of ADT is known as DESTIN, a multivariate unsupervised change detection for high dimensional time-series data of originally low effective dimension, which provides near real-time state assessment of network devices. The efficiency of the proposed approach is demonstrated and compared with well-known methodologies on an experimental test-bed. The method's performance is also explored extensively considering different criteria such as traffic type, device and the type of events to identify its potentials and limitations. The datasets used for the evaluation are made publicly available. (10.1016/j.comnet.2022.109474)
  DOI : 10.1016/j.comnet.2022.109474
• DNA code from cyclic and skew cyclic codes over F 4 [v]/⟨v 3 ⟩
  
  • Prakash Om
  • Singh Ashutosh
  • Verma Ram Krishna
  • Solé Patrick
  • Cheng Wei
  Entropy, MDPI, 2023. The main motivation of this work is to study and obtain some reversible and DNA codes of length n with better parameters. Here, we first investigate the structure of cyclic and skew cyclic codes over the chain ring R : = F 4 [ v ] / ⟨ v 3 ⟩ . We show an association between the codons and the elements of R using a Gray map. Under this Gray map, we study reversible and DNA codes of length n. Finally, several new DNA codes are obtained that have improved parameters than previously known codes. We also determine the Hamming and the Edit distances of these codes. (10.3390/e25020239)
  DOI : 10.3390/e25020239
• Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient
  
  • Fercoq Olivier
  Open Journal of Mathematical Optimization, Centre Mersenne, 2023, 4, pp.1-34. We study the linear convergence of the primal-dual hybrid gradient method. After a review of current analyses, we show that they do not explain properly the behavior of the algorithm, even on the most simple problems. We thus introduce the quadratic error bound of the smoothed gap, a new regularity assumption that holds for a wide class of optimization problems. Equipped with this tool, we manage to prove tighter convergence rates. Then, we show that averaging and restarting the primal-dual hybrid gradient allows us to leverage better the regularity constant. Numerical experiments on linear and quadratic programs, ridge regression and image denoising illustrate the findings of the paper. (10.5802/ojmo.26)
  DOI : 10.5802/ojmo.26
• Locally differentially private estimation of nonlinear functionals of discrete distributions
  
  • Butucea Cristina
  • Issartel Yann
  Advances in Neural Information Processing Systems, Morgan Kaufmann Publishers, 2023. We study the problem of estimating non-linear functionals of discrete distributions in the context of local differential privacy. The initial data $x_1,\ldots,x_n \in [K]$ are supposed i.i.d. and distributed according to an unknown discrete distribution $p = (p_1,\ldots,p_K)$. Only $\alpha$-locally differentially private (LDP) samples $z_1,...,z_n$ are publicly available, where the term 'local' means that each $z_i$ is produced using one individual attribute $x_i$. We exhibit privacy mechanisms (PM) that are interactive (i.e. they are allowed to use already published confidential data) or non-interactive. We describe the behavior of the quadratic risk for estimating the power sum functional $F_{\gamma} = \sum_{k=1}^K p_k^{\gamma}$, $\gamma >0$ as a function of $K, \, n$ and $\alpha$. In the non-interactive case, we study two plug-in type estimators of $F_{\gamma}$, for all $\gamma >0$, that are similar to the MLE analyzed by Jiao et al. (2017) in the multinomial model. However, due to the privacy constraint the rates we attain are slower and similar to those obtained in the Gaussian model by Collier et al. (2020). In the interactive case, we introduce for all $\gamma >1$ a two-step procedure which attains the faster parametric rate $(n \alpha^2)^{-1/2}$ when $\gamma \geq 2$. We give lower bounds results over all $\alpha$-LDP mechanisms and all estimators using the private samples.
• Scaling by subsampling for big data, with applications to statistical learning
  
  • Bertail Patrice
  • Bouchouia Mohammed
  • Jelassi Ons
  • Tressou Jessica
  • Zetlaoui Mélanie
  Journal of Nonparametric Statistics, American Statistical Association, 2023, 36 (1), pp.78-117. Handling large datasets and calculating complex statistics on huge datasets require important computing resources. Using subsampling methods to calculate statistics of interest on small samples is often used in practice to reduce computational complexity, for instance using the divide and conquer strategy. In this article, we recall some results on subsampling distributions and derive a precise rate of convergence for these quantities and the corresponding quantiles. We also develop some standardization techniques based on subsampling unstandardized statistics in the framework of large datasets. It is argued that using several subsampling distributions with different subsampling sizes brings a lot of information on the behavior of statistical learning procedures: subsampling allows to estimate the rate of convergence of different algorithms, to estimate the variability of complex statistics, to estimate confidence intervals for out-of-sample errors and interpolate their values at larger scales. These results are illustrated on simulations, but also on two important datasets, frequently analyzed in the statistical learning community, EMNIST (recognition of digits) and VeReMi (analysis of Network Vehicular Reference Misbehavior). (10.1080/10485252.2023.2219782)
  DOI : 10.1080/10485252.2023.2219782
• Multi-Agent Systems
  
  • Malvone Vadim
  • Murano Aniello
  , 2023, 14282, pp.XX-554. This volume LNCS 14282 constitutes the refereed proceedings of the 20th European Conference EUMAS 2023, held in Naples, Italy, during September 2023. This volume includes 24 full papers and 5 short papers, carefully selected from 47 submissions. Additionally, the volume features 16 short papers, rigorously reviewed from 20 submissions for the PhD day. The conference focused on the theory and practice of autonomous agents and multi-agent systems, covering a wide range of topics. (10.1007/978-3-031-43264-4)
  DOI : 10.1007/978-3-031-43264-4
• Execution trace analysis for a precise understanding of latency violations
  
  • Zoor Maysam
  • Apvrille Ludovic
  • Pacalet Renaud
  • Coudert Sophie
  Software and Systems Modeling, Springer Verlag, 2023. Despite the amount of proposed works for the verification of embedded systems, understanding the root cause of violations of requirements in simulation or execution traces is still an openissue, especially when dealing with temporal properties such as latencies. Is the violation due to an unfavorable real-time scheduling, to contentions on buses, to the characteristics of functional algorithms or hardware components? The paper introduces the Precise Latency ANalysis approach (PLAN), a new trace analysis technique whose objective is to classify execution transactions according to their impact on latency. To do so, we rely first on a model transformation that builds up a dependency graph from an allocation model, thus including hardware and software aspects of a system model. Then, from this graph and an execution trace, our analysis can highlight how software or hardware elements contributed to the latency violation. The paper first formalizes the problem before applying our approach to simulation traces of SysML models. A case study defined in the AQUAS European project illustrates the relevance of our approach. Last, a performance evaluation gives computation times for several models and requirements. (10.1007/s10270-022-01076-z)
  DOI : 10.1007/s10270-022-01076-z
• Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation
  
  • Li Tianyu
  • Roy Subhankar
  • Zhou Huayi
  • Lu Hongtao
  • Lathuilière Stéphane
  , 2023. To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous approaches have attempted to reduce the gap either at the pixel or feature level, disregarding the fact that the two components interact positively. To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation. We introduce well-estimated prototypes by including category-wise cross-domain information to link the two alignments: the pixel-level alignment is achieved using the jointly trained style transfer module with the prototypical semantic consistency, while the feature-level alignment is enforced to cross-domain features with the \textbf{pixel-to-prototype contrast}. Our extensive experiments demonstrate that our method outperforms existing state-of-the-art methods using DeepLabV2. Our code is available at https://github.com/cxa9264/CONFETI
• PrivacyGAN: robust generative image privacy
  
  • Zameshina Mariia
  • Careil Marlene
  • Teytaud Olivier
  • Najman Laurent
  , 2023. Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression. In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications. Drawing inspiration from Fawkes, our method entails shifting the original image within the embedding space towards a decoy image. We evaluate our approach using privacy metrics on traditional and novel facial image datasets. Additionally, we propose new criteria for evaluating the robustness of privacy-protection methods against unknown image recognition techniques, and we demonstrate that our approach is effective even in unknown embedding transfer scenarios. We also provide a human evaluation that further proves that the modified image preserves its utility as it remains recognisable as an image of the same person by friends and family.
• Knowledge Bases and Language Models: Complementing Forces
  
  • Suchanek Fabian M.
  • Luu Anh Tuan
  , 2023. Large language models (LLMs), as a particular instance of generative articial intelligence, have revolutionized natural language processing. In this invited paper, we argue that LLMs are complementary to structured data repositories such as databases or knowledge bases, which use symbolic knowledge representations. Hence, the two ways of knowledge representation will likely continue to co-exist, at least in the near future. We discuss ways that have been explored to make the two approaches work together, and point out opportunities and challenges for their symbiosis.