158 citations · 528 across the 70 of their papers we have counts for
18 papers · 1 filter
Learned-Database Systems Security
Roei Schuster, Jin Peng Zhou, Thorsten Eisenhofer +2
A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learn…
Private Multi-Winner Voting for Machine Learning
Adam Dziedzic, Christopher A Choquette-Choo, Natalie Dullerud +6
Private multi-winner voting is the task of revealing -hot binary vectors satisfying a bounded differential privacy (DP) guarantee. This task has been understudied in machine lea…
Verifiable and Provably Secure Machine Unlearning
Thorsten Eisenhofer, Doreen Riepel, Varun Chandrasekaran +3
Machine unlearning aims to remove points from the training dataset of a machine learning model after training: e.g., when a user requests their data to be deleted. While many unlea…
In Differential Privacy, There is Truth: On Vote Leakage in Ensemble Private Learning
Jiaqi Wang, Roei Schuster, Ilia Shumailov +2
When learning from sensitive data, care must be taken to ensure that training algorithms address privacy concerns. The canonical Private Aggregation of Teacher Ensembles, or PATE,…
Dataset Inference for Self-Supervised Models
Adam Dziedzic, Haonan Duan, Muhammad Ahmad Kaleem +5
Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream appli…
Proof-of-Learning is Currently More Broken Than You Think
Congyu Fang, Hengrui Jia, Anvith Thudi +5
Proof-of-Learning (PoL) proposes that a model owner logs training checkpoints to establish a proof of having expended the computation necessary for training. The authors of PoL for…
Generative Extraction of Audio Classifiers for Speaker Identification
Tejumade Afonja, Lucas Bourtoule, Varun Chandrasekaran +2
It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well…
-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations
Adam Dziedzic, Stephan Rabanser, Mohammad Yaghini +3
The lack of well-calibrated confidence estimates makes neural networks inadequate in safety-critical domains such as autonomous driving or healthcare. In these settings, having the…
Efficient Adversarial Training With Data Pruning
Maximilian Kaufmann, Yiren Zhao, Ilia Shumailov +2
Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial exa…
Intrinsic Anomaly Detection for Multi-Variate Time Series
Stephan Rabanser, Tim Januschowski, Kashif Rasul +6
We introduce a novel, practically relevant variation of the anomaly detection problem in multi-variate time series: intrinsic anomaly detection. It appears in diverse practical sce…
On the Difficulty of Defending Self-Supervised Learning against Model Extraction
Adam Dziedzic, Nikita Dhawan, Muhammad Ahmad Kaleem +2
Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These…
Architectural Backdoors in Neural Networks
Mikel Bober-Irizar, Ilia Shumailov, Yiren Zhao +2
Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedur…
On the Limitations of Stochastic Pre-processing Defenses
Yue Gao, Ilia Shumailov, Kassem Fawaz +1
Defending against adversarial examples remains an open problem. A common belief is that randomness at inference increases the cost of finding adversarial inputs. An example of such…
Selective Prediction via Training Dynamics
Stephan Rabanser, Anvith Thudi, Kimia Hamidieh +5
Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted…
Bounding Membership Inference
Anvith Thudi, Ilia Shumailov, Franziska Boenisch +1
Differential Privacy (DP) is the de facto standard for reasoning about the privacy guarantees of a training algorithm. Despite the empirical observation that DP reduces the vulnera…
Differentially Private Speaker Anonymization
Ali Shahin Shamsabadi, Brij Mohan Lal Srivastava, Aurélien Bellet +5
Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal da…
Tubes Among Us: Analog Attack on Automatic Speaker Identification
Shimaa Ahmed, Yash Wani, Ali Shahin Shamsabadi +4
Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial…
Increasing the Cost of Model Extraction with Calibrated Proof of Work
Adam Dziedzic, Muhammad Ahmad Kaleem, Yu Shen Lu +1
In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predi…