We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches.
We quantify the robustness of a trained network to input uncertainties with a stochastic simulation inspired by the field of Statistical Reliability Engineering.
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).
This document proposes an alternative proof of the result contained in article "High intrinsic dimensionality facilitates adversarial attack: Theoretical evidence", Amsaleg et a..
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks.
Group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member.
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.
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input.
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.
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.
The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches.
Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built.
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.
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.
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.