7 code implementations • 4 Jun 2018 • Ahmed Salem, Yang Zhang, Mathias Humbert, Pascal Berrang, Mario Fritz, Michael Backes
In addition, we propose the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.
1 code implementation • 5 May 2020 • Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, Yang Zhang
More importantly, we show that our attack in multiple cases outperforms the classical membership inference attack on the original ML model, which indicates that machine unlearning can have counterproductive effects on privacy.
1 code implementation • 27 Mar 2021 • Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, Yang Zhang
In this paper, we propose GraphEraser, a novel machine unlearning framework tailored to graph data.
1 code implementation • 15 Jan 2019 • Spyros Boukoros, Mathias Humbert, Stefan Katzenbeisser, Carmela Troncoso
Crowdsourcing enables application developers to benefit from large and diverse datasets at a low cost.
Cryptography and Security
1 code implementation • 30 Sep 2022 • Ziqing Yang, Xinlei He, Zheng Li, Michael Backes, Mathias Humbert, Pascal Berrang, Yang Zhang
Extensive evaluations on different datasets and model architectures show that all three attacks can achieve significant attack performance while maintaining model utility in both visual and linguistic modalities.
no code implementations • 1 Jan 2021 • Ahmed Salem, Yannick Sautter, Michael Backes, Mathias Humbert, Yang Zhang
We extend the applicability of backdoor attacks to autoencoders and GAN-based models.
no code implementations • 6 Oct 2020 • Ahmed Salem, Yannick Sautter, Michael Backes, Mathias Humbert, Yang Zhang
We extend the applicability of backdoor attacks to autoencoders and GAN-based models.
no code implementations • 18 Dec 2022 • Zeyang Sha, Xinlei He, Pascal Berrang, Mathias Humbert, Yang Zhang
Backdoor attacks represent one of the major threats to machine learning models.
no code implementations • 7 Feb 2024 • Daniel Celeny, Loïc Maréchal, Evgueni Rousselot, Alain Mermoud, Mathias Humbert
We find that the magnitude of abnormal returns around cyber incidents is on par with previous studies using newswire or alternative data to identify cyber incidents.
no code implementations • 7 Feb 2024 • Loïc Maréchal, Alain Mermoud, Dimitri Percia David, Mathias Humbert
We observe firms, their primary and secondary activities, funding rounds, and pre and post-money valuations.