[Accueil]
Curriculum vitae [fr] [en]
Jan Aalmoes
jaalmoes.com, jan@asgt.fr, 06.37.69.00.40

Keywords

Measure theory, Probability, Artificial intelligence, fairness, privacy, information theory, topological data analysis

In short

My main focus is applying theoretical math to improve data privacy whether it is in machine learning or in computer protocols. I have proved theoretical guarantees of the privacy and the reliability of sequential privacy identifiers for the LoRaWAN protocol. I have also shown multiple theoretical results linking fairness and privacy in machine learning.

My new research project is at the interface of topological data analysis and differential privacy ! I am currently looking for a postdoctoral position to move on with the project, if you are interested, please contact me.

Publications

On the Alignment of Group Fairness with Attribute Privacy, Jan Aalmoes, Vasisht Duddu and Antoine Boutet, Wise 2024.

In this paper, we have shown how attribute inference attack can be mitigated using fairness properties, namely demographic parity. I have shown multiple relations between those notions and I have introduced generalized demographic parity which extends the notion to non-discrete random variables. More details can be found in my phd thesis (in French)

Privacy-Preserving Pseudonyms for LoRaWAN, Samuel Pélissier, Jan Aalmoes, Abhishek Kumar Mishra, Mathieu Cunche, Vincent Roca, and Didier Donsez, Wisec 2024

In this contribution we have updated and secured the LoRaWAN protocol. My contribution is a probabilistic analysis of the collisions of data packets. It leads to an extensive theoretical development with the creation of a new probability law for which I computed the moments, the mass function and the cumulative distribution function. Because of page limits I could not include all of it in the paper but I plan on publishing them at some point. Here is the preprint.

MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers, Antoine Boutet, Thomas Lebrun, Jan Aalmoes, Adrien Baud, Middleware 2022.

In this paper we have developed a federated learning protocol that masks sensitive attributes of the updates. My contribution to this work was to prove that the new protocol does not deteriorate utility of the final machine learning model.

Workshops

Fairness and sensitive attribute inference, Jan Aalmoes, Antoine Boutet, Workshop @ Comète on Ethical AI, 2023, L'X, Palaiseau, Paris, France.

In this short 15 minutes presentation I have shown how demographic parity is equivalent to have a maximum of balanced accuracy equal to 1 m where m is the number of sensitive attributes.

Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attacks Jan Aalmoes, Vasisht Duddu, Antoine Boutet, APVP 2022 : 12ème Atelier sur la Protection de la Vie Privée

In this presentation I explored how regularisation parameters in exponentiated gradient descent for fair classification (https://proceedings.mlr.press/v80/agarwal18a.html) impacts the success of attribute inference attack.

Machine learning, or how to build a racist, sexist and unprivate world, Jan Aalmoes, Antoine Boutet, 2022, 6th Winter School Distributed Systems and Networks, GDR RSD and ACM SIGOPS France

I presented early experimental results showing issues and conflicts between fairness and privacy. I have shown the on many real world dataset we observe that a random forest behaves differently of different subgroups of a population based on sensitive attributes. It led to building an attribute inference attack that leverage soft labels of random forests.

Pre-publications

Reconciliating differential privacy and demographic parity with the help of synthetic data, Chapitre 7, section 7.2 de mon manuscrit de thèse.

There is a tradeoff between privacy and fairness in machine learning. In this paper I explore how those notions can be aligned by using intermediate generated synthetic data. To do so requires some theoretical work in topology:

Adapting the behaviour knowledge space method to maximize balanced accuracy, Chapitre 4 de mon manuscrit de thèse.

In this paper I introduce a new ensemble learning algorithm that maximizes balanced accuracy instead of accuracy. 1 # F i F P ( Y ̂ = i Y = i ) It then takes into account class imbalance during training. As explained in my phd manuscript, this algorithm is useful in auditing sensitive attribute leakage of the users of machine learning models.

Mass function of the number of coin flips to get m consecutive heads, Jan Aalmoes. The paper

This is a theoretical paper that solves the following problem: we throw a coin and look at the number of time we draw heads. How many time do we have to throw the coin before obtaining m times head on a row? In the paper, I compute the probability law of the number of throws before obtaining a sequence of uninterrupted heads. This work is crucial in reliability engineering and we applied it to the study of LoRaWAN.

Teaching

I was a tutorial instructor in mathematics at INSA-Lyon for two years. I was under the supervision of Romaric Pujol. I was in charge of a group of 30 first year students. The lessons were in English because the students were part of an international program (SCiences & ANglais (SCAN))

Algebra

  1. Linear Systems
  2. Vector Spaces
  3. Linear Maps
  4. Matrices
  5. Determinants
  6. Diagonalization of Endomorphisms

Calculus

  1. Sum, Product, Binomial Theorem
  2. Elementary Trigonometry
  3. Real Functions
  4. Limits
  5. Continuity
  6. Derivation
  7. Linear Differential Equations
  8. Comparison of Functions
  9. Taylor Expansions
  10. Riemann Integrals
  11. Fixed Point Theorem

Administration

From September 2021 to June 2024, Doctoral delegate in the council of the CITI-lab.

The council has the role to enforce democracy in the decisions taken by the president of the laboratory. The competence is broad and goes from quality of life to ethical and political orientations. Here are some examples of actual preoccupations:

Education