Evolutionary Algorithm-based images, humanly indistinguishable and adversarial against Convolutional Neural Networks: efficiency and filter robustness

in IEEE Access (2021)

Le rôle civilisationnel des universités

Article for general public (2021)

Privacy-Preserving Logistic Regression as a Cloud Service Based on Residue Number System

in Voevodin, Vladimir; Sobolev, Sergey (Eds.) 6th Russian Supercomputing Days, Moscow 21-22 September 2020 (2020, December)

A proof of concept to deceive humans and machines at image classification with evolutionary algorithms

in Chitic, Iona Raluca; Bernard, Nicolas; Leprévost, Franck (Eds.) Proceedings of ACIIDS 2020 (2020)

Reducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition

in 5th International Conference on Information Technology, Bangsaen 21-22 October 2020 (2020)

James Bond's Most Secret Weapon

in Proceedings of the 3rd International Conference on Applications in Information Technology (2018)

This conference presents in a non-conventional way secret-key and public-key cryptology from its origins to the present days.

Evolutionary Algorithms for Convolutional Neural Network Visualisation

in Meneses, Esteban; Castro, Harold; Barrios Hernández, Carlos Jaime (Eds.) et al High Performance Computing -- 5th Latin American Conference, CARLA 2018, Piedecuesta, Colombia (2018)

Deep Learning is based on deep neural networks trained over huge sets of examples. It enabled computers to compete with ---~or even outperform~--- humans at many tasks, from playing Go to driving ... [more ▼]

Deep Learning is based on deep neural networks trained over huge sets of examples. It enabled computers to compete with ---~or even outperform~--- humans at many tasks, from playing Go to driving vehicules. Still, it remains hard to understand how these networks actually operate. While an observer sees any individual local behaviour, he gets little insight about their global decision-making process. However, there is a class of neural networks widely used for image processing, convolutional networks, where each layer contains features working in parallel. By their structure, these features keep some spatial information across a network's layers. Visualisation of this spatial information at different locations in a network, notably on input data that maximise the activation of a given feature, can give insights on the way the model works. This paper investigates the use of Evolutionary Algorithms to evolve such input images that maximise feature activation. Compared with some pre-existing approaches, ours seems currently computationally heavier but with a wider applicability. [less ▲]

Hardened Bloom Filters, with an Application to Unobservability

in Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica (2013), 12(4), 11-22

Classical Bloom filters may be used to elegantly check if an element e belongs to a set S, and, if not, to add e to S. They do not store any data and only provide boolean answers regarding the membership ... [more ▼]

Classical Bloom filters may be used to elegantly check if an element e belongs to a set S, and, if not, to add e to S. They do not store any data and only provide boolean answers regarding the membership of a given element in the set, with some probability of false positive answers. Bloom filters are often used in caching system to check that some requested data actually exist before doing a costly lookup to retrieve them. However, security issues may arise for some other applications where an active attacker is able to inject data crafted to degrade the filters’ algorithmic properties, resulting for instance in a Denial of Service (DoS) situation. This leads us to the concept of hardened Bloom filters, combining classical Bloom filters with cryptographic hash functions and secret nonces. We show how this approach is successfully used in the TrueNyms unobservability system and protects it against replay attacks. [less ▲]

Beyond Tor: The TrueNyms Protocol

in Security and Intelligent Information Systems (2012)

Jacobians of genus 2 curves with a rational point of order 11

in Experimental Mathematics (2009), 18(1), 65-70

On the one hand, it is well-known that Jacobians of (hyper)elliptic curves defined over $\Q$ having a rational point of order $l$ can be used in many applications, for instance in the construction of ... [more ▼]

On the one hand, it is well-known that Jacobians of (hyper)elliptic curves defined over $\Q$ having a rational point of order $l$ can be used in many applications, for instance in the construction of class groups of quadratic fields with a non-trivial $l$-rank. On the other hand, it is also well-known that $11$ is the least prime number which is not the order of a rational point of an elliptic curve defined over $\Q$. It is therefore interesting to look for curves of higher genus, whose Jacobians have a rational point of order $11$. This problem has already been addressed, and Flynn found such a family $\Fl_t$ of genus $2$ curves. Now, it turns out, that the Jacobian $J_0(23)$ of the modular genus $2$ curve $X_0(23)$ has the required property, but does not belong to $\Fl_t$. The study of $X_0(23)$ leads to a method to partially solving the considered problem. Our approach allows us to recover $X_0(23)$, and to construct another $18$ distinct explicit curves of genus $2$ defined over $\Q$ and whose Jacobians have a rational point of order $11$. Of these $19$ curves, $10$ do not have any rational Weierstrass point, and $9$ have a rational Weierstrass point. None of these curves are $\Qb$-isomorphic to each other, nor $\Qb$-isomorphic to an element of Flynn's family $\Fl_t$. Finally, the Jacobians of these new curves are absolutely simple. [less ▲]