USENIX

Extracting Training Data from Large Language Models

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

TPM-FAIL: TPM meets Timing and Lattice Attacks

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Managing Memory Tiers with CXL in Virtualized Environments

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

High Accuracy and High Fidelity Extraction of Neural Networks

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: ...
USENIX

SREcon24 Europe/Middle East/Africa

SREcon is a gathering of engineers who care deeply about site reliability, systems engineering, and working with complex distributed systems at scale. SREcon strives to challenge both those new to the ...
USENIX

Practical Byzantine Fault Tolerance

This paper describes a new replication algorithm that is able to tolerate Byzantine faults. We believe that Byzantine-fault-tolerant algorithms will be increasingly important in the future because ...
USENIX

Transparent GPU Sharing in Container Clouds for Deep Learning Workloads

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

RETBLEED: Arbitrary Speculative Code Execution with Return Instructions

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Orca: A Distributed Serving System for Transformer-Based Generative Models

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Ansor: Generating High-Performance Tensor Programs for Deep Learning

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are ...
USENIX

Systematic Evaluation of Privacy Risks of Machine Learning Models

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the ...