Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Guaranteeing Local Differential Privacy on Ultra-Low-Power Systems
Published in ISCA, 2018 (Full Paper | bibtex | Plain Text)
We show that low resolution and fixed point nature of ultra-low-power implementations prevent privacy guarantees from being provided due to low quality noising. We present techniques, resampling and thresholding, to overcome this limitation.
Game of Threads: Enabling Asynchronous Poisoning Attacks
Published in ASPLOS, 2020 (Full Paper | bibtex | Plain Text)
Our attack influences training outcome—e.g., degrades model accuracy or biases the model towards an adversary-specified label—purely by scheduling asynchronous training threads in a malicious fashion. Since thread scheduling is outside the protections of modern trusted execution environments (TEEs), e.g., Intel SGX, our attack bypasses these protections even when the training set can be verified as correct.
PyTorchFI: A Runtime Perturbation Tool for DNNs
Published in DSML, 2020 (Full Paper | bibtex | Plain Text)
PyTorchFI is a runtime perturbation tool for deep neural networks (DNNs), implemented for the popular PyTorch deep learning platform. PyTorchFI enables users to perform perturbations on weights or neurons of DNNs at runtime.
Double-Cross Attacks: Subverting Active Learning Systems
Published in Usenix, 2021 (Full Paper | bibtex | Plain Text)
We present a novel attack called Double Cross, which aims to manipulate data labeling and model training in active learning settings.
Opening Pandora’s Box: A Systematic Study of New Ways Microarchitecture Can Leak Private Data
Published in ISCA, 2021 (Full Paper | bibtex | Plain Text)
Our study uncovers seven classes of microarchitectural optimization with novel security implications, proposes a conceptual framework through which to study them and demonstrates several proofs-of-concept to show their efficacy. The optimizations we study range from those that leak as much privacy as Spectre/Meltdown (but without exploiting speculative execution) to those that otherwise undermine security-critical programs in a variety of ways.
Augury: Using data memory-dependent prefetchers to leak data at rest
Published in IEEE S&P, 2022 (Full Paper | bibtex | Plain Text)
Our experiments demonstrate the existence of a pointer-chasing DMP on recent Apple processors, including the A14 and M1. We then reverse engineer the details of this DMP to determine the opportunities for and restrictions it places on attackers using it. Finally, we demonstrate several basic attack primitives capable of leaking pointer values using the DMP.
talks
Sensor Privacy in an Untrusted World
Published:
Presented an early version of “Guaranteeing Local Differential Privacy on Ultra-Low-Power Systems,” as Part of the Lawrence Technological University Alumni Career Series.
Game of Threads: Enabling Asynchronous Poisoning Attacks
Published:
Presentation for “Game of Threads: Enabling Asynchronous Poisoning Attacks,” at ASPLOS’20
Double-Cross Attacks: Subverting Active Learning Systems
Published:
Presentation for “Double-Cross Attacks: Subverting Active Learning Systems,” at Usenix’21
Opening Pandora’s Box: A Systematic Study of New Ways Microarchitecture Can Leak Private Data
Published:
Presentation for “Opening Pandora’s Box: A Systematic Study of New Ways Microarchitecture Can Leak Private Data,” at ISCA’21
Augury: Using data memory-dependent prefetchers to leak data at rest
Published:
Presentation for “Augury: Using data memory-dependent prefetchers to leak data at rest,” at IEEE S&P’22
Augury: Using data memory-dependent prefetchers to leak data at rest
Published:
Poster presentation for “Augury: Using data memory-dependent prefetchers to leak data at rest,” at the CSAW’22 Applied Research Competition. Our work was runner up.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.