AIConfPaper
← Search

Muhammad Ahmad Kaleem

5 accepted papers

2024

Memorization in Self-Supervised Learning Improves Downstream Generalization

Wenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes, Nicolas Papernot, Franziska Boenisch
ICLR 2024poster

Self-supervised learning (SSL) has recently received significant attention due to its ability to train high-performance encoders purely on unlabeled data---often scraped from the internet. This data can still be sensitive and empirical evidence suggests that SSL encoders memorize private information…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2023

Robust and Actively Secure Serverless Collaborative Learning

Nicholas Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, Mark R. Thomas, Muhammad Ahmad Kaleem, Stephan Rabanser +4
NeurIPS 2023poster

Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively protect user data, they remain vulnerable to either the server, the clients, or both, deviating from the protocol. Indeed, be…

Cited by 4Source ↗PDF ↗Scholar ↗
2022

Dataset Inference for Self-Supervised Models

Adam Dziedzic, Haonan Duan, Muhammad Ahmad Kaleem, Nikita Dhawan, Jonas Guan, Yannis Cattan +2
NeurIPS 2022accept

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 applications, they are increasingly used as a service exposed via public APIs. At the same time, these encoder models are par…

Cited by 36Source ↗PDF ↗Scholar ↗
2022

Increasing the Cost of Model Extraction with Calibrated Proof of Work

Adam Dziedzic, Muhammad Ahmad Kaleem, Yu Shen Lu, Nicolas Papernot
ICLR 2022spotlight

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 predictions. To prevent model stealing, existing defenses focus on detecting malicious queries, truncating, or distorting out…

Cited by 35Source ↗PDF ↗Scholar ↗
2022

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

Adam Dziedzic, Nikita Dhawan, Muhammad Ahmad Kaleem, Jonas Guan, Nicolas Papernot
ICML 2022spotlight

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 representations encode similarity structures that enable efficient learning of multiple downstream tasks. Recently, ML-a…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗