Florian Tramèr

发表

On Adaptive Attacks to Adversarial Example Defenses pdf

Aleksander Madry, Wieland Brendel, Nicholas Carlini, 2020, NeurIPS.

Advances and Open Problems in Federated Learning pdf

Richard Nock, Zaïd Harchaoui, David Evans, 2019, Found. Trends Mach. Learn..

Enter the Hydra: Towards Principled Bug Bounties and Exploit-Resistant Smart Contracts

Ari Juels, Florian Tramèr, Lorenz Breidenbach, 2018, IACR Cryptol. ePrint Arch..

Ensemble Adversarial Training: Attacks and Defenses pdf

Dan Boneh, Patrick McDaniel, Nicolas Papernot, 2017, ICLR.

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness pdf

Jörn-Henrik Jacobsen, Nicholas Carlini, Nicolas Papernot, 2019, ArXiv.

Stealing Machine Learning Models via Prediction APIs

Fan Zhang, Michael K. Reiter, Thomas Ristenpart, 2016, USENIX Security Symposium.

The Space of Transferable Adversarial Examples pdf

Dan Boneh, Patrick D. McDaniel, Nicolas Papernot, 2017, ArXiv.

FairTest: Discovering Unwarranted Associations in Data-Driven Applications

Roxana Geambasu, Vaggelis Atlidakis, Jean-Pierre Hubaux, 2015, 2017 IEEE European Symposium on Security and Privacy (EuroS&P).

On Solving LPN using BKW and Variants Implementation and Analysis

Florian Tramèr, S. Vaudenay, Sonia Bogos, 2015 .

Label-Only Membership Inference Attacks

Nicholas Carlini, Nicolas Papernot, Florian Tramèr, 2020, ICML.

A ug 2 02 1 NeuraCrypt is not private

Florian Tramèr, Nicholas Carlini, S. Jha, 2021 .

SquirRL: Automating Attack Analysis on Blockchain Incentive Mechanisms with Deep Reinforcement Learning

A. Juels, Florian Tramèr, Yan Ji, 2021, NDSS.

Extracting Training Data from Large Language Models pdf

Colin Raffel, Dawn Song, Eric Wallace, 2020, USENIX Security Symposium.

SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems

Florian Tramèr, Edward Chou, Giancarlo Pellegrino, 2018, 2020 IEEE Security and Privacy Workshops (SPW).

Measuring Forgetting of Memorized Training Examples

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2022, ArXiv.

On Adaptive Attacks to Adversarial Example Defenses

Florian Tramèr, A. Madry, Nicholas Carlini, 2020, NeurIPS.

Increasing Confidence in Adversarial Robustness Evaluations

Roland S. Zimmermann, Florian Tramèr, Nicholas Carlini, 2022, NeurIPS.

Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them

Florian Tramèr, 2021, ICML.

(Certified!!) Adversarial Robustness for Free!

J. Z. Kolter, Florian Tramèr, Nicholas Carlini, 2022, ArXiv.

Large Language Models Can Be Strong Differentially Private Learners

Tatsunori B. Hashimoto, Florian Tramèr, Percy Liang, 2021, ICLR.

Algorithmic Fairness Revisited

Florian Tramèr, 2015 .

Large Language Models Can Be Strong Differentially Private Learners

Tatsunori B. Hashimoto, Florian Tramèr, Percy Liang, 2021, ICLR.

Red-Teaming the Stable Diffusion Safety Filter

Florian Tramèr, David Lindner, Javier Rando, 2022, ArXiv.

Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets

Florian Tramèr, Nicholas Carlini, Hoang M. Le, 2022, CCS.

Red-Teaming the Stable Diffusion Safety Filter

Florian Tramèr, David Lindner, Javier Rando, 2022, ArXiv.

SquirRL: Automating Attack Discovery on Blockchain Incentive Mechanisms with Deep Reinforcement Learning pdf

Ari Juels, Yan Ji, Giulia Fanti, 2019, Proceedings 2021 Network and Distributed System Security Symposium.

NeuraCrypt is not private pdf

Somesh Jha, Sanjam Garg, Nicholas Carlini, 2021, ArXiv.

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.

Extracting Training Data from Large Language Models

Colin Raffel, Dawn Song, Eric Wallace, 2020, USENIX Security Symposium.

Addressing Beacon re-identification attacks: quantification and mitigation of privacy risks

Xiaoqian Jiang, Lucila Ohno-Machado, Jean-Pierre Hubaux, 2017, J. Am. Medical Informatics Assoc..

Poisoning Web-Scale Training Datasets is Practical

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2023, ArXiv.

Considerations for Differentially Private Learning with Large-Scale Public Pretraining

Florian Tramèr, Nicholas Carlini, Gautam Kamath, 2022, ArXiv.

Data Poisoning Won't Save You From Facial Recognition

Florian Tramèr, Evani Radiya-Dixit, 2021, ICLR.

Discovering Unwarranted Associations in Data-Driven Applications with the FairTest Testing Toolkit pdf

Roxana Geambasu, Vaggelis Atlidakis, Jean-Pierre Hubaux, 2015, ArXiv.

SentiNet: Detecting Physical Attacks Against Deep Learning Systems pdf

Dan Boneh, Edward Chou, Florian Tramèr, 2018, ArXiv.

Quantifying Memorization Across Neural Language Models

Florian Tramèr, Nicholas Carlini, Chiyuan Zhang, 2022, ICLR.

What Does it Mean for a Language Model to Preserve Privacy?

Florian Tramèr, R. Shokri, Katherine Lee, 2022, FAccT.

The Privacy Onion Effect: Memorization is Relative

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2022, NeurIPS.

Differentially Private Learning Needs Better Features (or Much More Data) pdf

Dan Boneh, Florian Tramer, Florian Tramèr, 2020, ICLR.

Membership Inference Attacks From First Principles

Florian Tramèr, Nicholas Carlini, A. Terzis, 2021, 2022 IEEE Symposium on Security and Privacy (SP).

Label-Only Membership Inference Attacks pdf

Nicolas Papernot, Florian Tramèr, Nicholas Carlini, 2020, ICML.

Extracting Training Data from Diffusion Models

Florian Tramèr, Nicholas Carlini, Borja Balle, 2023, USENIX Security Symposium.

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware pdf

Dan Boneh, Florian Tramèr, Florian Tramèr, 2018, ICLR.

Counterfactual Memorization in Neural Language Models pdf

Daphne Ippolito, Nicholas Carlini, Florian Tramer, 2021, ArXiv.

Physical Adversarial Examples for Object Detectors pdf

Dawn Song, Ivan Evtimov, Tadayoshi Kohno, 2018, WOOT @ USENIX Security Symposium.

Sealed-Glass Proofs: Using Transparent Enclaves to Prove and Sell Knowledge

Fan Zhang, Elaine Shi, Jean-Pierre Hubaux, 2017, 2017 IEEE European Symposium on Security and Privacy (EuroS&P).

Measuring Forgetting of Memorized Training Examples

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2022, ICLR.

Security of Machine Learning

Florian Tramèr, Nicholas Carlini, D. Song, 2019 .

SNAP: Efficient Extraction of Private Properties with Poisoning

Florian Tramèr, Jonathan Ullman, Alina Oprea, 2022, ArXiv.

(Certified!!) Adversarial Robustness for Free!

J. Z. Kolter, Florian Tramèr, Nicholas Carlini, 2022, ICLR.

Adversarial Training and Robustness for Multiple Perturbations

Dan Boneh, Florian Tramèr, Florian Tramèr, 2019, NeurIPS.

Debugging Differential Privacy: A Case Study for Privacy Auditing

Florian Tramèr, Nicholas Carlini, A. Terzis, 2022, ArXiv.

Antipodes of Label Differential Privacy: PATE and ALIBI pdf

Florian Tramer, Florian Tramèr, Igor Shilov, 2021, NeurIPS.

Is Private Learning Possible with Instance Encoding?

Somesh Jha, Sanjam Garg, Nicholas Carlini, 2021, 2021 IEEE Symposium on Security and Privacy (SP).

Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2022, ArXiv.

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations pdf

Jorn-Henrik Jacobsen, Nicolas Papernot, Nicholas Carlini, 2020, ICML.

Note on Attacking Object Detectors with Adversarial Stickers pdf

Atul Prakash, Dawn Xiaodong Song, Amir Rahmati, 2017, ArXiv.

PrivateRide: A Privacy-Enhanced Ride-Hailing Service

Jean-Pierre Hubaux, Virgil D. Gligor, Kévin Huguenin, 2017, Proc. Priv. Enhancing Technol..

Tight Auditing of Differentially Private Machine Learning

Florian Tramèr, Nicholas Carlini, A. Terzis, 2023, USENIX Security Symposium.

Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2022, ArXiv.

Formal Abstractions for Attested Execution Secure Processors

Elaine Shi, Rafael Pass, Florian Tramèr, 2017, EUROCRYPT.

Evaluating Superhuman Models with Consistency Checks

Florian Tramèr, Daniel Paleka, Lukas Fluri, 2023, ArXiv.

SNAP: Efficient Extraction of Private Properties with Poisoning

Florian Tramèr, Jonathan Ullman, Alina Oprea, 2022, 2023 IEEE Symposium on Security and Privacy (SP).

Evading Black-box Classifiers Without Breaking Eggs

Florian Tramèr, Nicholas Carlini, Edoardo Debenedetti, 2023, 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).

Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems

Florian Tramèr, Nicholas Carlini, Chawin Sitawarin, 2022, ArXiv.

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning

Dan Boneh, Florian Tramèr, Pascal Dupré, 2019, CCS.

Differential Privacy with Bounded Priors: Reconciling Utility and Privacy in Genome-Wide Association Studies

Zhicong Huang, Jean-Pierre Hubaux, Erman Ayday, 2015, CCS.

Q UANTIFYING M EMORIZATION A CROSS N EURAL L ANGUAGE M ODELS

Florian Tramèr, Nicholas Carlini, Katherine Lee, 2023 .

Are aligned neural networks adversarially aligned?

Pang Wei Koh, Christopher A. Choquette-Choo, Florian Tramèr, 2023, NeurIPS.

Randomness in ML Defenses Helps Persistent Attackers and Hinders Evaluators

Florian Tramèr, Nicholas Carlini, Lujo Bauer, 2023, ArXiv.

M EASURING F ORGETTING OF M EMORIZED T RAINING E XAMPLES

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2023 .

Stealing Machine Learning Models via Prediction APIs

A. Juels, Florian Tramèr, Fan Zhang, 2016, USENIX Security Symposium.

An Attack on InstaHide: Is Private Learning Possible with Instance Encoding? pdf

Somesh Jha, Sanjam Garg, Shuang Song, 2020, ArXiv.

Remote Side-Channel Attacks on Anonymous Transactions

Kenneth G. Paterson, Dan Boneh, Florian Tramèr, 2020, IACR Cryptol. ePrint Arch..

SquirRL: Automating Attack Discovery on Blockchain Incentive Mechanisms with Deep Reinforcement Learning pdf

Ari Juels, Florian Tramer, Giulia Fanti, 2019, ArXiv.

The Hydra Framework for Principled, Automated Bug Bounties

Ari Juels, Florian Tramer, Lorenz Breidenbach, 2019, IEEE Security & Privacy.

PING and REJECT: The Impact of Side-Channels on Zcash Privacy

Florian Tramèr, K. Paterson, 2019 .

Extracting Training Data from Large Language Models

Tom B. Brown, Florian Tramèr, Nicholas Carlini, 2020, USENIX Security Symposium.

Privacy Side Channels in Machine Learning Systems

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2023, ArXiv.

Counterfactual Memorization in Neural Language Models

Florian Tramèr, Nicholas Carlini, Katherine Lee, 2021, NeurIPS.

Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy

Florian Tramèr, Nicholas Carlini, Katherine Lee, 2022, INLG.

Backdoor Attacks for In-Context Learning with Language Models

Florian Tramèr, Nicholas Carlini, Matthew Jagielski, 2023, ArXiv.

Evaluating Superhuman Models with Consistency Checks

Florian Tramèr, Daniel Paleka, Lukas Fluri, 2023, ArXiv.

Scalable Extraction of Training Data from (Production) Language Models

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2023, ArXiv.

Tight Auditing of Differentially Private Machine Learning

Florian Tramèr, Nicholas Carlini, A. Terzis, 2023, USENIX Security Symposium.