Jose Rodrigo Sanchez Vicarte

Jose Rodrigo Sanchez Vicarte

Hardware Security Researcher at Intel's Security Assurance and Cryptography group.

Publications

@inproceedings{10.1145/3373376.3378462,
author = {Sanchez Vicarte, Jose Rodrigo and Schreiber, Benjamin and Paccagnella, Riccardo and Fletcher, Christopher W.},
title = {Game of Threads: Enabling Asynchronous Poisoning Attacks},
year = {2020},
isbn = {9781450371025},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3373376.3378462},
doi = {10.1145/3373376.3378462},
booktitle = {Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems},
pages = {35–52},
numpages = {18},
keywords = {adversarial machine learning, trusted execution environment, asynchronous stochastic gradient descent},
location = {Lausanne, Switzerland},
series = {ASPLOS ’20}
}
Jose Rodrigo Sanchez Vicarte, Benjamin Schreiber, Riccardo Paccagnella, and Christopher W. Fletcher. 2020. Game of Threads: Enabling Asynchronous Poisoning Attacks. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS ’20). Association for Computing Machinery, New York, NY, USA, 35–52. DOI:https://doi.org/10.1145/3373376.3378462
@inproceedings{inproceedings,
author = {Mahmoud, Abdulrahman and Aggarwal, Neeraj and Nobbe, Alex and Vicarte, Jose and Adve, Sarita and Fletcher, Christopher and Frosio, Iuri and Hari, Siva},
year = {2020},
month = {06},
pages = {25-31},
title = {PyTorchFI: A Runtime Perturbation Tool for DNNs},
doi = {10.1109/DSN-W50199.2020.00014}
}
Mahmoud, Abdulrahman & Aggarwal, Neeraj & Nobbe, Alex & Vicarte, Jose & Adve, Sarita & Fletcher, Christopher & Frosio, Iuri & Hari, Siva. (2020). PyTorchFI: A Runtime Perturbation Tool for DNNs.
@INPROCEEDINGS{9499823, author={Sanchez Vicarte, Jose Rodrigo and Shome, Pradyumna and Nayak, Nandeeka and Trippel, Caroline and Morrison, Adam and Kohlbrenner, David and Fletcher, Christopher W.}, booktitle={2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA)}, title={Opening Pandora’s Box: A Systematic Study of New Ways Microarchitecture Can Leak Private Data}, year={2021}, volume={}, number={}, pages={347-360}, doi={10.1109/ISCA52012.2021.00035}}
J. R. Sanchez Vicarte et al., "Opening Pandora’s Box: A Systematic Study of New Ways Microarchitecture Can Leak Private Data," 2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), 2021, pp. 347-360, doi: 10.1109/ISCA52012.2021.00035.
@inproceedings {274693, author = {Jose Rodrigo Sanchez Vicarte and Gang Wang and Christopher W. Fletcher}, title = {Double-Cross Attacks: Subverting Active Learning Systems}, booktitle = {30th USENIX Security Symposium (USENIX Security 21)}, year = {2021}, isbn = {978-1-939133-24-3}, pages = {1593--1610}, url = {https://www.usenix.org/conference/usenixsecurity21/presentation/vicarte}, publisher = {USENIX Association}, month = aug, }
Jose Rodrigo Sanchez Vicarte and Gang Wang and Christopher W. Fletcher. Double-Cross Attacks: Subverting Active Learning Systems. In Proceedings of the 30th USENIX Security Symposium (USENIX Security 21), August 21-24, 2021, San Jose, CA, USA, 1593-1610.
@inproceedings{augury:2022:vicarte:oakland22, title={Augury: Using Data Memory-Dependent Prefetchers to Leak Data at Rest}, author={Jose Rodrigo Sanchez Vicarte and Michael Flanders and Riccardo Paccagnella and Grant Garrett-Grossman and Adam Morrison and Christopher W. Fletcher and David Kohlbrenner }, booktitle={2022 IEEE Symposium on Security and Privacy (SP)}, year={2022}, organization={IEEE Computer Society} }
J. Sanchez Vicarte, et al., "Augury: Using data memory-dependent prefetchers to leak data at rest," in 2022 2022 IEEE Symposium on Security and Privacy (SP) (SP), San Francisco, CA, US, 2022.
@inproceedings{10.1109/ISCA.2018.00053,
author = {Choi, Woo-Seok and Tomei, Matthew and Vicarte, Jose Rodrigo Sanchez and Hanumolu, Pavan Kumar and Kumar, Rakesh},
title = {Guaranteeing Local Differential Privacy on Ultra-Low-Power Systems},
year = {2018},
isbn = {9781538659847},
publisher = {IEEE Press},
url = {https://doi.org/10.1109/ISCA.2018.00053},
doi = {10.1109/ISCA.2018.00053},
booktitle = {Proceedings of the 45th Annual International Symposium on Computer Architecture},
pages = {561–574},
numpages = {14},
keywords = {microcontrollers, randomized response, IoT, low-power systems, RAPPOR, differential privacy},
location = {Los Angeles, California},
series = {ISCA ’18}
}
Woo-Seok Choi, Matthew Tomei, Jose Rodrigo Sanchez Vicarte, Pavan Kumar Hanumolu, and Rakesh Kumar. 2018. Guaranteeing local differential privacy on ultra-low-power systems. In Proceedings of the 45th Annual International Symposium on Computer Architecture (ISCA ’18). IEEE Press, 561–574. DOI:https://doi.org/10.1109/ISCA.2018.00053

Augury: Using data memory-dependent prefetchers to leak data at rest

Published in IEEE S&P, 2022 (Full Paper | bibtex | Plain Text)

Our experiments demonstrate the existence of a pointer-chasing DMP on recent Apple processors, including the A14 and M1. We then reverse engineer the details of this DMP to determine the opportunities for and restrictions it places on attackers using it. Finally, we demonstrate several basic attack primitives capable of leaking pointer values using the DMP.

Opening Pandora’s Box: A Systematic Study of New Ways Microarchitecture Can Leak Private Data

Published in ISCA, 2021 (Full Paper | bibtex | Plain Text)

Our study uncovers seven classes of microarchitectural optimization with novel security implications, proposes a conceptual framework through which to study them and demonstrates several proofs-of-concept to show their efficacy. The optimizations we study range from those that leak as much privacy as Spectre/Meltdown (but without exploiting speculative execution) to those that otherwise undermine security-critical programs in a variety of ways.

Game of Threads: Enabling Asynchronous Poisoning Attacks

Published in ASPLOS, 2020 (Full Paper | bibtex | Plain Text)

Our attack influences training outcome—e.g., degrades model accuracy or biases the model towards an adversary-specified label—purely by scheduling asynchronous training threads in a malicious fashion. Since thread scheduling is outside the protections of modern trusted execution environments (TEEs), e.g., Intel SGX, our attack bypasses these protections even when the training set can be verified as correct.