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...
share
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...
research
∙
07/01/2023
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Differentially private stochastic gradient descent (DP-SGD) is the canon...
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...
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...
research
∙
05/28/2023
Training Private Models That Know What They Don't Know
Training reliable deep learning models which avoid making overconfident ...
research
∙
05/27/2023
The Curse of Recursion: Training on Generated Data Makes Models Forget
Stable Diffusion revolutionised image creation from descriptive text. GP...
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,...
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...
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 ...
research
∙
01/09/2023
Is Federated Learning a Practical PET Yet?
Federated learning (FL) is a framework for users to jointly train a mach...
research
∙
12/20/2022
Learned Systems Security
A learned system uses machine learning (ML) internally to improve perfor...
research
∙
11/23/2022
Private Multi-Winner Voting for Machine Learning
Private multi-winner voting is the task of revealing k-hot binary vector...
research
∙
10/17/2022
Verifiable and Provably Secure Machine Unlearning
Machine unlearning aims to remove points from the training dataset of a ...
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...
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...
research
∙
09/16/2022
Dataset Inference for Self-Supervised Models
Self-supervised models are increasingly prevalent in machine learning (M...
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...
research
∙
07/26/2022
Generative Extraction of Audio Classifiers for Speaker Identification
It is perhaps no longer surprising that machine learning models, especia...
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...
research
∙
07/01/2022
Efficient Adversarial Training With Data Pruning
Neural networks are susceptible to adversarial examples-small input pert...
research
∙
06/29/2022
Intrinsic Anomaly Detection for Multi-Variate Time Series
We introduce a novel, practically relevant variation of the anomaly dete...
research
∙
06/21/2022
The Privacy Onion Effect: Memorization is Relative
Machine learning models trained on private datasets have been shown to l...
research
∙
06/19/2022
On the Limitations of Stochastic Pre-processing Defenses
Defending against adversarial examples remains an open problem. A common...
research
∙
06/15/2022
Architectural Backdoors in Neural Networks
Machine learning is vulnerable to adversarial manipulation. Previous lit...
research
∙
05/26/2022
Selective Classification Via Neural Network Training Dynamics
Selective classification is the task of rejecting inputs a model would p...
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...
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...
research
∙
02/24/2022
Bounding Membership Inference
Differential Privacy (DP) is the de facto standard for reasoning about t...
research
∙
02/23/2022
Differentially Private Speaker Anonymization
Sharing real-world speech utterances is key to the training and deployme...
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...
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...
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...
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...
research
∙
10/07/2021
Hyperparameter Tuning with Renyi Differential Privacy
For many differentially private algorithms, such as the prominent noisy ...
research
∙
09/27/2021
Unrolling SGD: Understanding Factors Influencing Machine Unlearning
Machine unlearning is the process through which a deployed machine learn...
research
∙
09/24/2021
Interpretability in Safety-Critical FinancialTrading Systems
Sophisticated machine learning (ML) models to inform trading in the fina...
research
∙
09/20/2021
SoK: Machine Learning Governance
The application of machine learning (ML) in computer systems introduces ...
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...
research
∙
06/18/2021
Bad Characters: Imperceptible NLP Attacks
Several years of research have shown that machine-learning systems are v...
research
∙
06/01/2021
Markpainting: Adversarial Machine Learning meets Inpainting
Inpainting is a learned interpolation technique that is based on generat...
research
∙
04/21/2021
Dataset Inference: Ownership Resolution in Machine Learning
With increasingly more data and computation involved in their training, ...
research
∙
04/19/2021
Manipulating SGD with Data Ordering Attacks
Machine learning is vulnerable to a wide variety of different attacks. I...
research
∙
03/09/2021
Proof-of-Learning: Definitions and Practice
Training machine learning (ML) models typically involves expensive itera...
research
∙
02/09/2021
CaPC Learning: Confidential and Private Collaborative Learning
Machine learning benefits from large training datasets, which may not 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...
research
∙
11/30/2020
Data-Free Model Extraction
Current model extraction attacks assume that the adversary has access to...
research
∙
11/02/2020
Adversarial Examples in Constrained Domains
Machine learning algorithms have been shown to be vulnerable to adversar...
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...
research
∙
08/20/2020