no code implementations • 22 Feb 2024 • Tom Sander, Pierre Fernandez, Alain Durmus, Matthijs Douze, Teddy Furon
This paper investigates the radioactivity of LLM-generated texts, i. e. whether it is possible to detect that such input was used as training data.
1 code implementation • 30 Jan 2024 • Robin San Roman, Pierre Fernandez, Alexandre Défossez, Teddy Furon, Tuan Tran, Hady Elsahar
In the rapidly evolving field of speech generative models, there is a pressing need to ensure audio authenticity against the risks of voice cloning.
no code implementations • 17 Oct 2023 • Pierre Fernandez, Guillaume Couairon, Teddy Furon, Matthijs Douze
The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance.
3 code implementations • 26 Jul 2023 • Pierre Fernandez, Antoine Chaffin, Karim TIT, Vivien Chappelier, Teddy Furon
The task of discerning between generated and natural texts is increasingly challenging.
1 code implementation • ICCV 2023 • Thibault Maho, Seyed-Mohsen Moosavi-Dezfooli, Teddy Furon
The transferability of adversarial examples is a key issue in the security of deep neural networks.
1 code implementation • ICCV 2023 • Pierre Fernandez, Guillaume Couairon, Hervé Jégou, Matthijs Douze, Teddy Furon
For instance, it detects the origin of an image generated from a text prompt, then cropped to keep $10\%$ of the content, with $90$+$\%$ accuracy at a false positive rate below 10$^{-6}$.
no code implementations • 6 Dec 2022 • Kassem Kallas, Teddy Furon
It is crucial to protect the intellectual property rights of DNN models prior to their deployment.
1 code implementation • 5 Oct 2022 • Pierre Fernandez, Matthijs Douze, Hervé Jégou, Teddy Furon
First, a neural network maps an image to a vector representation, that is relatively robust to various transformations of the image.
no code implementations • 5 Aug 2022 • Thibault Maho, Teddy Furon, Erwan Le Merrer
We achieve both goals by demonstrating that benign inputs, that are unmodified images, for instance, are sufficient material for both tasks.
no code implementations • 22 Jun 2022 • Kassem Kallas, Teddy Furon
Protecting the Intellectual Property rights of DNN models is of primary importance prior to their deployment.
no code implementations • 17 Jun 2022 • Marzieh Gheisari, Javad Amirian, Teddy Furon, Laurent Amsaleg
In some face recognition applications, we are interested to verify whether an individual is a member of a group, without revealing their identity.
no code implementations • 28 Apr 2022 • Thibault Maho, Teddy Furon, Erwan Le Merrer
We first formally highlight the mismatch between a theoretical certification and the practice of attacks on classifiers.
1 code implementation • 17 Dec 2021 • Pierre Fernandez, Alexandre Sablayrolles, Teddy Furon, Hervé Jégou, Matthijs Douze
We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches.
1 code implementation • NeurIPS 2021 • Karim TIT, Teddy Furon, Mathias Rousset
We quantify the robustness of a trained network to input uncertainties with a stochastic simulation inspired by the field of Statistical Reliability Engineering.
1 code implementation • 10 Feb 2021 • Thibault Maho, Benoît Bonnet, Teddy Furon, Erwan Le Merrer
Many defenses have emerged with the development of adversarial attacks.
1 code implementation • CVPR 2021 • Thibault Maho, Teddy Furon, Erwan Le Merrer
This paper presents SurFree, a geometrical approach that achieves a similar drastic reduction in the amount of queries in the hardest setup: black box decision-based attacks (only the top-1 label is available).
no code implementations • 2 Oct 2020 • Teddy Furon
This paper investigates the vulnerability of the nearest neighbors search, which is a pivotal tool in data analysis and machine learning.
no code implementations • 12 Aug 2020 • Wenqing Liu, Miaojing Shi, Teddy Furon, Li Li
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks.
no code implementations • 24 Feb 2020 • Marzieh Gheisari, Teddy Furon, Laurent Amsaleg
This paper proposes a framework for group membership protocols preventing the curious but honest server from reconstructing the enrolled biometric signatures and inferring the identity of querying clients.
no code implementations • 24 Feb 2020 • Marzieh Gheisari, Teddy Furon, Laurent Amsaleg
Group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member.
1 code implementation • 4 Dec 2019 • Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input.
no code implementations • 23 Apr 2019 • Marzieh Gheisari, Teddy Furon, Laurent Amsaleg
When convoking privacy, group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member.
1 code implementation • 28 Mar 2019 • Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg
This paper investigates the visual quality of the adversarial examples.
no code implementations • 23 Jul 2018 • Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondrej Chum
State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line.
no code implementations • 21 Apr 2017 • Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum
Location recognition is commonly treated as visual instance retrieval on "street view" imagery.
1 code implementation • CVPR 2018 • Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondrej Chum
This makes the Euclidean nearest neighbor search biased for this task.
3 code implementations • CVPR 2017 • Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum
The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches.
no code implementations • 14 Nov 2016 • Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frederic Jurie
Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built.
no code implementations • CVPR 2016 • Ahmet Iscen, Michael Rabbat, Teddy Furon
Experiments with standard image search benchmarks, including the Yahoo100M dataset comprising 100 million images, show that our method gives comparable (and sometimes superior) accuracy compared to exhaustive search while requiring only 10% of the vector operations and memory.
no code implementations • 10 Dec 2014 • Ahmet Iscen, Teddy Furon, Vincent Gripon, Michael Rabbat, Hervé Jégou
We study an indexing architecture to store and search in a database of high-dimensional vectors from the perspective of statistical signal processing and decision theory.
no code implementations • 8 Jul 2014 • Giorgos Tolias, Teddy Furon, Hervé Jégou
Our geometric-aware aggregation strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.