Florian Tramèr
Publications by Year
Research Areas
Adversarial Robustness in Machine Learning, Privacy-Preserving Technologies in Data, Advanced Malware Detection Techniques, Topic Modeling, Cryptography and Data Security
Most-Cited Works
- → Advances and Open Problems in Federated Learning(2020)4,353 cited
- → On the Opportunities and Risks of Foundation Models(2021)2,134 cited
- Ensemble Adversarial Training: Attacks and Defenses(2017)
- → Stealing Machine Learning Models via Prediction APIs(2016)733 cited
- → The Space of Transferable Adversarial Examples(2017)435 cited
- → Membership Inference Attacks From First Principles(2022)360 cited
- → Extracting Training Data from Large Language Models(2020)274 cited
- → Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware(2018)226 cited
- → FairTest: Discovering Unwarranted Associations in Data-Driven Applications(2017)161 cited