( en | de | ru )

 

Disambiguation

From post

копироватьудалитьдобавить публикацию в буфер
Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets.

, , , , , , и . CCS, стр. 2779-2792. ACM, (2022)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

Erwin Tramer

Gottfried Tramer

Michael Tramer

Florian Klasovsky

Syntheseparameter-Reaktivitätsbeziehungen für neue Palladiumoxidkatalysatoren in feinchemischen Hydrierungen. TU Darmstadt, (2009)

Florian Franz

Realzeittest von Fahrzeugsoftware-Komponenten. TU München, (2009)
 

Другие публикации лиц с тем же именем

An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?, , , , , , , , и . CoRR, (2020)Evaluating Superhuman Models with Consistency Checks., , и . CoRR, (2023)Poisoning Web-Scale Training Datasets is Practical., , , , , , , , и . CoRR, (2023)Measuring Forgetting of Memorized Training Examples., , , , , , , , , и 1 other автор(ы). CoRR, (2022)Debugging Differential Privacy: A Case Study for Privacy Auditing., , , , , и . CoRR, (2022)Red-Teaming the Stable Diffusion Safety Filter., , , , и . CoRR, (2022)Enter the Hydra: Towards Principled Bug Bounties and Exploit-Resistant Smart Contracts., , , и . USENIX Security Symposium, стр. 1335-1352. USENIX Association, (2018)Label-Only Membership Inference Attacks., , , и . ICML, том 139 из Proceedings of Machine Learning Research, стр. 1964-1974. PMLR, (2021)The Privacy Onion Effect: Memorization is Relative., , , , , и . NeurIPS, (2022)Increasing Confidence in Adversarial Robustness Evaluations., , , и . NeurIPS, (2022)