78 citations · 237 across the 21 of their papers we have counts for
22 papers
Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
Haonan Duan, Adam Dziedzic, Nicolas Papernot +1
Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these conce…
Have it your way: Individualized Privacy Assignment for DP-SGD
Franziska Boenisch, Christopher Mühl, Adam Dziedzic +2
When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by…
Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation
Franziska Boenisch, Adam Dziedzic, Roei Schuster +3
Federated learning (FL) is a framework for users to jointly train a machine learning model. FL is promoted as a privacy-enhancing technology (PET) that provides data minimization:…
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…
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…
-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…
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…
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…
Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees
Franziska Boenisch, Christopher Mühl, Roy Rinberg +2
Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP)…
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…
When the Curious Abandon Honesty: Federated Learning Is Not Private
Franziska Boenisch, Adam Dziedzic, Roei Schuster +3
In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. Instead, these devices share gradients, parameters, or oth…
On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples
Adelin Travers, Lorna Licollari, Guanghan Wang +4
Machine learning (ML) models are known to be vulnerable to adversarial examples. Applications of ML to voice biometrics authentication are no exception. Yet, the implications of au…
CaPC Learning: Confidential and Private Collaborative Learning
Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic +4
Machine learning benefits from large training datasets, which may not always be possible to collect by any single entity, especially when using privacy-sensitive data. In many cont…
Pretrained Transformers Improve Out-of-Distribution Robustness
Dan Hendrycks, Xiaoyuan Liu, Eric Wallace +3
Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribut…
Machine Learning enabled Spectrum Sharing in Dense LTE-U/Wi-Fi Coexistence Scenarios
Adam Dziedzic, Vanlin Sathya, Muhammad Iqbal Rochman +2
The application of Machine Learning (ML) techniques to complex engineering problems has proved to be an attractive and efficient solution. ML has been successfully applied to sever…
Analysis of Random Perturbations for Robust Convolutional Neural Networks
Adam Dziedzic, Sanjay Krishnan
Recent work has extensively shown that randomized perturbations of neural networks can improve robustness to adversarial attacks. The literature is, however, lacking a detailed com…
Machine Learning based detection of multiple Wi-Fi BSSs for LTE-U CSAT
Vanlin Sathya, Adam Dziedzic, Monisha Ghosh +1
According to the LTE-U Forum specification, a LTE-U base-station (BS) reduces its duty cycle from 50% to 33% when it senses an increase in the number of co-channel Wi-Fi basic serv…
Band-limited Training and Inference for Convolutional Neural Networks
Adam Dziedzic, John Paparrizos, Sanjay Krishnan +2
The convolutional layers are core building blocks of neural network architectures. In general, a convolutional filter applies to the entire frequency spectrum of the input data. We…
Testing Robustness Against Unforeseen Adversaries
Max Kaufmann, Daniel Kang, Yi Sun +9
Adversarial robustness research primarily focuses on L_p perturbations, and most defenses are developed with identical training-time and test-time adversaries. However, in real-wor…
DeepLens: Towards a Visual Data Management System
Sanjay Krishnan, Adam Dziedzic, Aaron J. Elmore
Advances in deep learning have greatly widened the scope of automatic computer vision algorithms and enable users to ask questions directly about the content in images and video. T…
Version 0.1 of the BigDAWG Polystore System
Vijay Gadepally, Kyle OBrien, Adam Dziedzic +7
A polystore system is a database management system (DBMS) composed of integrated heterogeneous database engines and multiple programming languages. By matching data to the storage…
BigDAWG Polystore Release and Demonstration
Kyle OBrien, Vijay Gadepally, Jennie Duggan +7
The Intel Science and Technology Center for Big Data is developing a reference implementation of a Polystore database. The BigDAWG (Big Data Working Group) system supports "many si…