Nicolas Papernot

research

∙ 09/05/2023

The Adversarial Implications of Variable-Time Inference

Machine learning (ML) models are known to be vulnerable to a number of a...

0 Dudi Biton, et al. ∙

research

∙ 07/20/2023

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

Large language models (LLMs) have exhibited impressive capabilities in c...

0 David Glukhov, et al. ∙

research

∙ 07/01/2023

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD

Differentially private stochastic gradient descent (DP-SGD) is the canon...

0 Anvith Thudi, et al. ∙

research

∙ 06/14/2023

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness

Machine learning models are susceptible to a variety of attacks that can...

0 Jiapeng Wu, et al. ∙

research

∙ 06/12/2023

When Vision Fails: Text Attacks Against ViT and OCR

While text-based machine learning models that operate on visual inputs o...

0 Nicholas Boucher, et al. ∙

research

∙ 05/28/2023

Training Private Models That Know What They Don't Know

Training reliable deep learning models which avoid making overconfident ...

0 Stephan Rabanser, et al. ∙

research

∙ 05/27/2023

The Curse of Recursion: Training on Generated Data Makes Models Forget

Stable Diffusion revolutionised image creation from descriptive text. GP...

0 Ilia Shumailov, et al. ∙

research

∙ 05/24/2023

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

Large language models (LLMs) are excellent in-context learners. However,...

0 Haonan Duan, et al. ∙

research

∙ 03/29/2023

Have it your way: Individualized Privacy Assignment for DP-SGD

When training a machine learning model with differential privacy, one se...

0 Franziska Boenisch, et al. ∙

research

∙ 02/17/2023

Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility

Deploying machine learning (ML) models often requires both fairness and ...

0 Mohammad Yaghini, et al. ∙

research

∙ 01/09/2023

Is Federated Learning a Practical PET Yet?

Federated learning (FL) is a framework for users to jointly train a mach...

10 Franziska Boenisch, et al. ∙

research

∙ 12/20/2022

Learned Systems Security

A learned system uses machine learning (ML) internally to improve perfor...

4 Roei Schuster, et al. ∙

research

∙ 11/23/2022

Private Multi-Winner Voting for Machine Learning

Private multi-winner voting is the task of revealing k-hot binary vector...

1 Adam Dziedzic, et al. ∙

research

∙ 10/17/2022

Verifiable and Provably Secure Machine Unlearning

Machine unlearning aims to remove points from the training dataset of a ...

5 Thorsten Eisenhofer, et al. ∙

research

∙ 10/05/2022

Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search

Models need to be trained with privacy-preserving learning algorithms to...

8 Yannis Cattan, et al. ∙

research

∙ 09/22/2022

In Differential Privacy, There is Truth: On Vote Leakage in Ensemble Private Learning

When learning from sensitive data, care must be taken to ensure that tra...

4 Jiaqi Wang, et al. ∙

research

∙ 09/16/2022

Dataset Inference for Self-Supervised Models

Self-supervised models are increasingly prevalent in machine learning (M...

7 Adam Dziedzic, et al. ∙

research

∙ 08/06/2022

On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning

Proof-of-learning (PoL) proposes a model owner use machine learning trai...

3 Congyu Fang, et al. ∙

research

∙ 07/26/2022

Generative Extraction of Audio Classifiers for Speaker Identification

It is perhaps no longer surprising that machine learning models, especia...

0 Tejumade Afonja, et al. ∙

research

∙ 07/25/2022

p-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations

The lack of well-calibrated confidence estimates makes neural networks i...

0 Adam Dziedzic, et al. ∙

research

∙ 07/01/2022

Efficient Adversarial Training With Data Pruning

Neural networks are susceptible to adversarial examples-small input pert...

0 Maximilian Kaufmann, et al. ∙

research

∙ 06/29/2022

Intrinsic Anomaly Detection for Multi-Variate Time Series

We introduce a novel, practically relevant variation of the anomaly dete...

0 Stephan Rabanser, et al. ∙

research

∙ 06/21/2022

The Privacy Onion Effect: Memorization is Relative

Machine learning models trained on private datasets have been shown to l...

0 Nicholas Carlini, et al. ∙

research

∙ 06/19/2022

On the Limitations of Stochastic Pre-processing Defenses

Defending against adversarial examples remains an open problem. A common...

0 Yue Gao, et al. ∙

research

∙ 06/15/2022

Architectural Backdoors in Neural Networks

Machine learning is vulnerable to adversarial manipulation. Previous lit...

0 Mikel Bober-Irizar, et al. ∙

research

∙ 05/26/2022

Selective Classification Via Neural Network Training Dynamics

Selective classification is the task of rejecting inputs a model would p...

0 Stephan Rabanser, et al. ∙

research

∙ 05/16/2022

On the Difficulty of Defending Self-Supervised Learning against Model Extraction

Self-Supervised Learning (SSL) is an increasingly popular ML paradigm th...

0 Adam Dziedzic, et al. ∙

research

∙ 03/23/2022

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Deep metric learning (DML) enables learning with less supervision throug...

0 Natalie Dullerud, et al. ∙

research

∙ 02/24/2022

Bounding Membership Inference

Differential Privacy (DP) is the de facto standard for reasoning about t...

0 Anvith Thudi, et al. ∙

research

∙ 02/23/2022

Differentially Private Speaker Anonymization

Sharing real-world speech utterances is key to the training and deployme...

2 Ali Shahin Shamsabadi, et al. ∙

research

∙ 02/06/2022

Pipe Overflow: Smashing Voice Authentication for Fun and Profit

Recent years have seen a surge of popularity of acoustics-enabled person...

6 Shimaa Ahmed, et al. ∙

research

∙ 01/23/2022

Increasing the Cost of Model Extraction with Calibrated Proof of Work

In model extraction attacks, adversaries can steal a machine learning mo...

0 Adam Dziedzic, et al. ∙

research

∙ 12/06/2021

When the Curious Abandon Honesty: Federated Learning Is Not Private

In federated learning (FL), data does not leave personal devices when th...

5 Franziska Boenisch, et al. ∙

research

∙ 10/22/2021

On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning

Machine unlearning, i.e. having a model forget about some of its trainin...

0 Anvith Thudi, et al. ∙

research

∙ 10/07/2021

Hyperparameter Tuning with Renyi Differential Privacy

For many differentially private algorithms, such as the prominent noisy ...

0 Nicolas Papernot, et al. ∙

research

∙ 09/27/2021

Unrolling SGD: Understanding Factors Influencing Machine Unlearning

Machine unlearning is the process through which a deployed machine learn...

4 Anvith Thudi, et al. ∙

research

∙ 09/24/2021

Interpretability in Safety-Critical FinancialTrading Systems

Sophisticated machine learning (ML) models to inform trading in the fina...

0 Gabriel Deza, et al. ∙

research

∙ 09/20/2021

SoK: Machine Learning Governance

The application of machine learning (ML) in computer systems introduces ...

5 Varun Chandrasekaran, et al. ∙

research

∙ 08/03/2021

On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples

Machine learning (ML) models are known to be vulnerable to adversarial e...

8 Adelin Travers, et al. ∙

research

∙ 06/18/2021

Bad Characters: Imperceptible NLP Attacks

Several years of research have shown that machine-learning systems are v...

0 Nicholas Boucher, et al. ∙

research

∙ 06/01/2021

Markpainting: Adversarial Machine Learning meets Inpainting

Inpainting is a learned interpolation technique that is based on generat...

0 David Khachaturov, et al. ∙

research

∙ 04/21/2021

Dataset Inference: Ownership Resolution in Machine Learning

With increasingly more data and computation involved in their training, ...

0 Pratyush Maini, et al. ∙

research

∙ 04/19/2021

Manipulating SGD with Data Ordering Attacks

Machine learning is vulnerable to a wide variety of different attacks. I...

14 Ilia Shumailov, et al. ∙

research

∙ 03/09/2021

Proof-of-Learning: Definitions and Practice

Training machine learning (ML) models typically involves expensive itera...

12 Hengrui Jia, et al. ∙

research

∙ 02/09/2021

CaPC Learning: Confidential and Private Collaborative Learning

Machine learning benefits from large training datasets, which may not al...

2 Christopher A. Choquette-Choo, et al. ∙

research

∙ 12/14/2020

Neighbors From Hell: Voltage Attacks Against Deep Learning Accelerators on Multi-Tenant FPGAs

Field-programmable gate arrays (FPGAs) are becoming widely used accelera...

0 Andrew Boutros, et al. ∙

research

∙ 11/30/2020

Data-Free Model Extraction

Current model extraction attacks assume that the adversary has access to...

0 Jean-Baptiste Truong, et al. ∙

research

∙ 11/02/2020

Adversarial Examples in Constrained Domains

Machine learning algorithms have been shown to be vulnerable to adversar...

8 Ryan Sheatsley, et al. ∙

research

∙ 10/13/2020

Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings

Machine learning models in health care are often deployed in settings wh...

0 Vinith M. Suriyakumar, et al. ∙

research

∙ 08/20/2020

Not My Deepfake: Towards Plausible Deniability for Machine-Generated Media

Progress in generative modelling, especially generative adversarial netw...

7 Baiwu Zhang, et al. ∙

Nicolas Papernot

Featured Co-authors