Post-doctoral Research Visit F/m Privacy-preserving
Il y a 6 mois
Le descriptif de l’offre ci-dessous est en Anglais_
**Type de contrat **:CDD
**Contrat renouvelable **:Oui
**Niveau de diplôme exigé **:Thèse ou équivalent
**Fonction **:Post-Doctorant
**A propos du centre ou de la direction fonctionnelle**:
The Inria centre at Université Côte d'Azur includes 37 research teams and 8 support services. The centre's staff (about 500 people) is made up of scientists of different nationalities, engineers, technicians and administrative staff. The teams are mainly located on the university campuses of Sophia Antipolis and Nice as well as Montpellier, in close collaboration with research and higher education laboratories and establishments (Université Côte d'Azur, CNRS, INRAE, INSERM...), but also with the regiona economic players.
With a presence in the fields of computational neuroscience and biology, data science and modeling, software engineering and certification, as well as collaborative robotics, the Inria Centre at Université Côte d'Azur is a major player in terms of scientific excellence through its results and collaborations at both European and international levels.
**Contexte et atouts du poste**:
not applicable
**Mission confiée**:
Context:
Federated Learning (FL) empowers a multitude of devices, including mobile phones and sensors, to collaboratively train a global machine learning model while retaining their data locally [1,2]. A prominent example of FL in action is Google's Gboard, which uses a FL-trained model to predict subsequent user inputs on smartphones [3].
Two primary challenges arise during the training phase of FL [4]:
**_ Data Privacy_**: _How to ensure user data remains confidential?_ Even though the data is kept locally by the devices, it has been shown that an honest-but-curious server can still reconstruct data samples [5,6], sensitive attributes [7,8], and the local model [9] of a targeted device. Moreover, the server can perform membership inference attacks [10] to identify whether a data sample was used in training or source inference attacks to determine which device stores a given data sample [11].
**_ Security Against Malicious Participants_**: _How to ensure the learning process is not derailed by harmful actors?_ Recent research has demonstrated that, in the absence of protective measures, a malicious agent can deteriorate model performance by simply flipping the labels [12] and/or the sign of the gradient [13], and even inject backdoors into the model [14] (backdoors are hidden vulnerabilities that can be exploited under certain conditions predefined by the attacker, such as specific inputs).
To enhance system security against adversarial threats, Byzantine resilient mechanisms are implemented on the server side. These algorithms are designed to identify and mitigate potentially detrimental actions or inputs from users, ensuring that even if some components act maliciously or erratically, the overall system remains functional and secure [21,22,23,24]. Experiments [21] reveal that integrating these Byzantine resilient mechanisms sustains neural network accuracy at 90.7%, even when 10% of the agents maliciously flip the labels on the MNIST dataset. In contrast, without such protection, the accuracy of the neural network drops significantly to 77.3%.
Integrating differential privacy with Byzantine resilience presents a notable challenge. Recent research suggests that when these two security measures are combined in their current forms, the effectiveness of the resulting algorithm disproportionately depends on the number of parameters (d) in the machine learning model [25]. In particular, it requires either the batch size to grow proportionally to the square root of d, or the proportion of the malicious agents in the system to decrease inversely proportional to the square root of d. For a realistic model such as ResNet-50 (with around 25 million parameters), the batch size should be larger than 5000, which is clearly impractical. To tackle this problem, novel Byzantine resilient algorithms have been recently proposed [26,27]. However, these algorithms encounter significant computational complexity, proportional to d3, at each communication round. **Hence, there is a pressing need for innovative methods that can seamlessly integrate differential privacy and Byzantine resilience with low computational complexity to train practical neural networks.**
Objective
In this project, we aim to propose novel FL algorithms to effectively tackle these two mutually linked challenges.
In particular we want to explore the potentialities of **compression** in FL training, as these techniques can highly reduce the model dimension, which **may provide a solution for a **_computation-efficient,_** **_private,_** and **_secure_** FL system.**
Compression techniques were initially introduced to alleviate communication costs in distributed training processes, where only a proportion of model parameters are sent from the device to the serv
-
Post-doctoral Research Visit F/m Reproducibility of
Il y a 2 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Contrat renouvelable **:Oui **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria Grenoble research center groups together almost 600 people in 23 research teams and 7 research...
-
Post-doctoral Research Visit F/m Distributed
Il y a 5 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD**Niveau de diplôme exigé **:Thèse ou équivalent**Fonction **:Post-DoctorantA propos du centre ou de la direction fonctionnelle The Inria centre at Université Côte d'Azur includes 37 research teams and 8 support services. The centre's staff (about 500 people) is made up of...
-
Post-doctoral Research Visit F/m Multigraded
il y a 3 semaines
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria center at Université Côte d'Azur includes 42 research teams and 9 support services. The center’s staff (about 500 people) is...
-
Post-doctoral Research Visit F/m Post-doctorant
il y a 3 semaines
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **Niveau d'expérience souhaité **:Jeune diplômé **A propos du centre ou de la direction fonctionnelle**: The Inria center at Université Côte d'Azur includes 42 research teams and 9 support services. The center’s...
-
Post-doctoral Research Visit F/m Post-doctorant
Il y a 5 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Niveau de diplôme exigé **:Thèse ou équivalent**Fonction **:Post-Doctorant**Niveau d'expérience souhaité **:Jeune diplôméA propos du centre ou de la direction fonctionnelle The Inria centre at Université Côte d'Azur includes 37 research teams and 8 support services. The centre's staff (about...
-
Post-doctoral Research Visit F/m Post-doctorant
Il y a 5 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **Niveau d'expérience souhaité **:Jeune diplômé **A propos du centre ou de la direction fonctionnelle**: The Inria centre at Université Côte d'Azur includes 37 research teams and 8 support services. The centre's...
-
Postdoctoral Research Visitor in Privacy-Preserving Federated Learning
il y a 3 semaines
Technopole de Sophia Antipolis, France INRIA Temps pleinProject OverviewAs a postdoctoral research visitor in our team, you will work on developing novel federated learning algorithms to address the challenges of privacy and security in distributed machine learning systems. Our goal is to create a secure and efficient federated learning framework that can be applied in various domains, including healthcare,...
-
Post-doctoral Research Visit F/m Generative Models
Il y a 5 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Contrat renouvelable **:Oui **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **Niveau d'expérience souhaité **:Jusqu'à 3 ans **A propos du centre ou de la direction fonctionnelle**: The Inria centre at Université Côte d'Azur includes...
-
Technopole de Sophia Antipolis, France INRIA Temps pleinContext and Advantages of the PositionThe postdoctoral researcher will work on developing novel federated learning algorithms that effectively tackle the challenges of protecting user privacy and ensuring robustness against adversarial threats. The researcher will explore the potentialities of compression in FL training, aiming to provide a solution for a...
-
Post-doctoral Research Visit F/m Exploring
Il y a 2 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria center at Université Côte d'Azur includes 42 research teams and 9 support services. The center’s staff (about 500 people) is...
-
Post-doctoral Research Visit F/m Postdoc Position
Il y a 3 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Contrat renouvelable **:Oui **Niveau de diplôme exigé **:Thèse ou équivalent **Fonction **:Post-Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria center at Université Côte d'Azur includes 42 research teams and 9 support services. The...
-
Cooperative Inference Strategies Post-Doctoral Research Visit
il y a 3 semaines
Technopole de Sophia Antipolis, France INRIA Temps pleinJob AnnouncementINRIA seeks a highly motivated postdoctoral researcher to join our team and contribute to the development of cooperative inference strategies for machine learning. The successful candidate will work closely with our experts in the field of computer science and applied mathematics to advance the state-of-the-art in inference delivery networks...
-
Postdoctoral Research Visit F/M Cooperative Inference Strategies
il y a 4 semaines
Technopole de Sophia Antipolis, France INRIA Temps pleinResearch Position in Cooperative Inference StrategiesThis postdoctoral research visit is part of the Inria-Nokia Bell Labs challenge LearnNet (Learning Networks). The researcher will work on inference delivery strategies in networks of computing nodes that coordinate to satisfy machine learning inference requests.Research GoalThe goal of this research is to...
-
Technopole de Sophia Antipolis, France INRIA Temps pleinContexte et atouts du poste Atlantis is a joint project-team between Inria and the Jean-Alexandre Dieudonné Mathematics Laboratory at Université Côte d'Azur. The team gathers applied mathematicians and computational scientists who are collaboratively undertaking research activities aiming at the design, analysis, development and application of...
-
Phd Position F/m Privacy On-demand and Security
Il y a 5 mois
Sophia Antipolis, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD**Niveau de diplôme exigé **:Bac + 5 ou équivalent**Fonction **:DoctorantA propos du centre ou de la direction fonctionnelle Le centre Inria d'Université Côte d'Azur regroupe 37 équipes de recherche et 8 services d’appui. Le personnel du centre (500 personnes environ) est...
-
Technopole de Sophia Antipolis, France INRIA Temps pleinContexte et atouts du poste Team SPARKS/WIMMICS Mission confiée In the context of the CIIAM project (Contextual Information Inference for Argument Mining), funded through the France 2030 investment plan managed by the National Research Agency (ANR), as part of the Initiative of Excellence Université Côte d’Azur, aiming to enhance the...
-
Technopole de Sophia Antipolis, France INRIA Temps pleinResearch Position Overview We are seeking a highly motivated postdoctoral researcher to join our team at INRIA and work on distributed machine learning at the network edge. The successful candidate will be part of the dAIEDGE project, a network of excellence for distributed, trustworthy, efficient, and scalable AI at the edge, funded by the European Union....
-
Technopole de Sophia Antipolis, France INRIA Temps pleinContext and Key Features of the PositionThe position involves investigating the intersection of differential privacy and Byzantine resilience in federated learning, with a focus on developing novel algorithms that can seamlessly integrate these two security measures with low computational complexity.Key ResponsibilitiesThe successful candidate will be...
-
Postdoctoral Research Visit F/M Cooperative Inference Strategies
il y a 4 semaines
Technopole de Sophia Antipolis, France INRIA Temps pleinResearch PositionThis postdoctoral research visit is part of the Inria-Nokia Bell Labs LearnNet challenge, focusing on cooperative inference strategies in machine learning. The successful candidate will work with a team of researchers to develop novel inference delivery networks, integrating machine learning models with different computational and memory...
-
Technopole de Sophia Antipolis, France INRIA Temps pleinJob Context and RequirementsThe position is part of the dAIEDGE project, a network of excellence for distributed, trustworthy, efficient, and scalable AI at the Edge, funded by the European Union.The dAIEDGE Network of Excellence aims to strengthen and support the development of the dynamic European edge AI ecosystem under the umbrella of the European AI...
