Get started
Author

Florian Tramèr

Observed names: Florian Simon Tramèr, Florian Tramer, Tramer Florian, Tramer, Florian, Tramèr, Florian
Institution: ETH Zurich
Observed institutions: Google (United States), University of Toronto, Peking University, ETH Zurich, Google (Switzerland), Cornell Tech, École Polytechnique Fédérale de Lausanne, Carnegie Mellon University, Stanford University
ORCID: 0000-0001-8703-8762
Observed ORCID: 0000-0001-8703-8762
OpenAlex ID: A5006851333
Advances and Open Problems in Federated Learning
2020 · Peter Kairouz, H. Brendan McMahan, et al. · Foundations and Trends® in Machine Learning · 6,341
PDF
On the Opportunities and Risks of Foundation Models
2021 · Bommasani, Rishi, Hudson, Drew A., et al. · arXiv (Cornell University) · 2,194
PDF
Ensemble Adversarial Training: Attacks and Defenses
2017 · Tramèr, Florian, Kurakin, Alexey, et al. · arXiv (Cornell University) · 2,138
PDF
Stealing Machine Learning Models via Prediction APIs
2016 · Tramèr, Florian, Zhang, Fan, et al. · arXiv (Cornell University) · 729
PDF
Membership Inference Attacks From First Principles
2022 · Nicholas Carlini, Steve Chien, et al. · Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · 503
PDF
The Space of Transferable Adversarial Examples
2017 · Tramèr, Florian, Papernot, Nicolas, et al. · arXiv (Cornell University) · 395
PDF
Extracting Training Data from Large Language Models
2020 · Carlini, Nicholas, Tramer, Florian, et al. · arXiv (Cornell University) · 270
PDF
SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems
2020 · Edward Chou, Florian Tramer, et al. · IEEE Security and Privacy Workshops (SPW) · 260
PDF
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
2018 · Tramèr, Florian, Boneh, Dan · arXiv (Cornell University) · 233
PDF
FairTest: Discovering Unwarranted Associations in Data-Driven Applications
2017 · Florian Tramer, Vaggelis Atlidakis, et al. · IEEE European Symposium on Security and Privacy · 167
PDF
Quantifying Memorization Across Neural Language Models
2022 · Carlini, Nicholas, Ippolito, Daphne, et al. · arXiv (Cornell University) · 161
PDF
What Does it Mean for a Language Model to Preserve Privacy?
2022 · Hannah Brown, Katherine Lee, et al. · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · 158
PDF
Poisoning Web-Scale Training Datasets is Practical
2024 · Nicholas Carlini, Matthew Jagielski, et al. · Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · 133
PDF
On Adaptive Attacks to Adversarial Example Defenses
2020 · Tramer, Florian, Carlini, Nicholas, et al. · arXiv (Cornell University) · 130
PDF
Adversarial Training and Robustness for Multiple Perturbations
2019 · Tramèr, Florian, Boneh, Dan · arXiv (Cornell University) · 122
PDF
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
2024 · Edoardo Debenedetti, Jie Zhang, et al. · neural information processing systems · 110
PrivateRide: A Privacy-Enhanced Ride-Hailing Service
2017 · Anh Pham, Italo Dacosta, et al. · Proceedings on Privacy Enhancing Technologies · 102
Formal Abstractions for Attested Execution Secure Processors
2017 · Rafael Pass, Elaine Shi, et al. · Lecture notes in computer science · 102
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
2024 · Patrick Chao, Edoardo Debenedetti, et al. · neural information processing systems · 96
PDF
Label-Only Membership Inference Attacks
2020 · Choquette-Choo, Christopher A., Tramer, Florian, et al. · arXiv (Cornell University) · 96
PDF
Physical Adversarial Examples for Object Detectors
2018 · Eykholt, Kevin, Evtimov, Ivan, et al. · arXiv (Cornell University) · 91
PDF
Extracting Training Data from Diffusion Models
2023 · Carlini, Nicholas, Hayes, Jamie, et al. · arXiv (Cornell University) · 89
PDF
Addressing Beacon re-identification attacks: quantification and mitigation of privacy risks
2016 · Jean Louis Raisaro, Florian Tramèr, et al. · Journal of the American Medical Informatics Association · 86
PDF
Sealed-Glass Proofs: Using Transparent Enclaves to Prove and Sell Knowledge
2017 · Florian Tramer, Fan Zhang, et al. · IEEE European Symposium on Security and Privacy · 85
Scalable Extraction of Training Data from (Production) Language Models
2023 · Nasr, Milad, Carlini, Nicholas, et al. · arXiv (Cornell University) · 82
PDF
Works count: 140
Citation count: 16,150
H-index: 36
I10-index: 62
Year
Topic
Type