Training data-efficient image transformers & distillation through attention H Touvron, M Cord, M Douze, F Massa, A Sablayrolles, H Jégou International conference on machine learning, 10347-10357, 2021 | 3226 | 2021 |
Going deeper with image transformers H Touvron, M Cord, A Sablayrolles, G Synnaeve, H Jégou Proceedings of the IEEE/CVF International Conference on Computer Vision, 32-42, 2021 | 554 | 2021 |
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference A Sablayrolles, M Douze, Y Ollivier, C Schmid, H Jégou International conference on Machine learning (ICML) 2019, 2019 | 205 | 2019 |
Opacus: User-friendly differential privacy library in PyTorch A Yousefpour, I Shilov, A Sablayrolles, D Testuggine, K Prasad, M Malek, ... NeurIPS 2021 Privacy workshop (PriML), 2021 | 117 | 2021 |
Large Memory Layers with Product Keys G Lample, A Sablayrolles, MA Ranzato, L Denoyer, H Jégou Advances in Neural Information Processing Systems (NeurIPS) 2019, 2019 | 102 | 2019 |
How should we evaluate supervised hashing? A Sablayrolles, M Douze, N Usunier, H Jégou International Conference on Acoustics, Speech and Signal Processing (ICASSP …, 2017 | 101 | 2017 |
Spreading vectors for similarity search A Sablayrolles, M Douze, C Schmid, H Jégou International Conference on Learning Representations (ICLR) 2019, 2018 | 73 | 2018 |
Radioactive data: tracing through training A Sablayrolles, M Douze, C Schmid, H Jégou International Conference on Machine Learning, 8326-8335, 2020 | 47 | 2020 |
Grafit: Learning fine-grained image representations with coarse labels H Touvron, A Sablayrolles, M Douze, M Cord, H Jégou Proceedings of the IEEE/CVF international conference on computer vision, 874-884, 2021 | 46 | 2021 |
Gradient-based adversarial attacks against text transformers C Guo, A Sablayrolles, H Jégou, D Kiela arXiv preprint arXiv:2104.13733, 2021 | 39 | 2021 |
Link and code: Fast indexing with graphs and compact regression codes M Douze, A Sablayrolles, H Jégou IEEE Conference on Computer Vision & Pattern Recognition (CVPR) 2018, 2018 | 39 | 2018 |
On the importance of difficulty calibration in membership inference attacks L Watson, C Guo, G Cormode, A Sablayrolles International Conference on Learning Representations (ICLR) 2022, 2021 | 22 | 2021 |
Déjà Vu: an empirical evaluation of the memorization properties of ConvNets A Sablayrolles, M Douze, C Schmid, H Jégou arXiv preprint arXiv:1809.06396, 2018 | 14 | 2018 |
Defending against Reconstruction Attacks with Rényi Differential Privacy P Stock, I Shilov, I Mironov, A Sablayrolles arXiv preprint arXiv:2202.07623, 2022 | 11 | 2022 |
Optimal membership inference bounds for adaptive composition of sampled gaussian mechanisms S Mahloujifar, A Sablayrolles, G Cormode, S Jha arXiv preprint arXiv:2204.06106, 2022 | 8 | 2022 |
TAN without a burn: Scaling Laws of DP-SGD T Sander, P Stock, A Sablayrolles arXiv preprint arXiv:2210.03403, 2022 | 7 | 2022 |
Fast indexing with graphs and compact regression codes on online social networks M Douze, A Sablayrolles, H Jegou US Patent 11,093,561, 2021 | 7 | 2021 |
Watermarking images in self-supervised latent spaces P Fernandez, A Sablayrolles, T Furon, H Jégou, M Douze ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 5 | 2022 |
Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano C Guo, A Sablayrolles, M Sanjabi arXiv preprint arXiv:2210.13662, 2022 | 3 | 2022 |
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning S Maddock, A Sablayrolles, P Stock arXiv preprint arXiv:2210.02912, 2022 | 2 | 2022 |