99 citations · 203 across the 21 of their papers we have counts for
21 papers
Physical Time-Lock Puzzles
Niloufar Sayadi, Chenglu Jin, Phuong Ha Nguyen +2
Traditional time-lock puzzles enforce delayed access to encrypted secrets by relying on inherently sequential computational steps. However, since software-based constructions impos…
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
Murat Bilgehan Ertan, Xiaochen Zhu, Phuong Ha Nguyen +2
We introduce PACZero, a family of PAC-private zeroth-order mechanisms for fine-tuning large language models that delivers usable utility at . This privacy regime…
Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Tasks
Murat Bilgehan Ertan, Ronak Sahu, Phuong Ha Nguyen +2
We introduce ROAR (Robust Object Removal and Re-annotation), a scalable framework for privacy-preserving dataset obfuscation that eliminates sensitive objects instead of modifying…
Breaking XOR Arbiter PUFs with Chosen Challenge Attack
Niloufar Sayadi, Phuong Ha Nguyen, Marten van Dijk +1
The XOR Arbiter PUF was introduced as a strong PUF in 2007 and was broken in 2015 by a Machine Learning (ML) attack, which allows the underlying Arbiter PUFs to be modeled individu…
Batch Clipping and Adaptive Layerwise Clipping for Differential Private Stochastic Gradient Descent
Toan N. Nguyen, Phuong Ha Nguyen, Lam M. Nguyen +1
Each round in Differential Private Stochastic Gradient Descent (DPSGD) transmits a sum of clipped gradients obfuscated with Gaussian noise to a central server which uses this to up…
Considerations on the Theory of Training Models with Differential Privacy
Marten van Dijk, Phuong Ha Nguyen
In federated learning collaborative learning takes place by a set of clients who each want to remain in control of how their local training data is used, in particular, how can eac…
Generalizing DP-SGD with Shuffling and Batch Clipping
Marten van Dijk, Phuong Ha Nguyen, Toan N. Nguyen +1
Classical differential private DP-SGD implements individual clipping with random subsampling, which forces a mini-batch SGD approach. We provide a general differential private algo…
Secure Remote Attestation with Strong Key Insulation Guarantees
Deniz Gurevin, Chenglu Jin, Phuong Ha Nguyen +2
Recent years have witnessed a trend of secure processor design in both academia and industry. Secure processors with hardware-enforced isolation can be a solid foundation of cloud…
Proactive DP: A Multple Target Optimization Framework for DP-SGD
Marten van Dijk, Nhuong V. Nguyen, Toan N. Nguyen +2
We introduce a multiple target optimization framework for DP-SGD referred to as pro-active DP. In contrast to traditional DP accountants, which are used to track the expenditure of…
Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizes
Marten van Dijk, Nhuong V. Nguyen, Toan N. Nguyen +3
Hogwild! implements asynchronous Stochastic Gradient Descent (SGD) where multiple threads in parallel access a common repository containing training data, perform SGD iterations an…
Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise
Marten van Dijk, Nhuong V. Nguyen, Toan N. Nguyen +3
The feasibility of federated learning is highly constrained by the server-clients infrastructure in terms of network communication. Most newly launched smartphones and IoT devices…
A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning
Nhan H. Pham, Lam M. Nguyen, Dzung T. Phan +3
We propose a novel hybrid stochastic policy gradient estimator by combining an unbiased policy gradient estimator, the REINFORCE estimator, with another biased one, an adapted SARA…
A Unified Convergence Analysis for Shuffling-Type Gradient Methods
Lam M. Nguyen, Quoc Tran-Dinh, Dzung T. Phan +2
In this paper, we propose a unified convergence analysis for a class of generic shuffling-type gradient methods for solving finite-sum optimization problems. Our analysis works wit…
BUZz: BUffer Zones for defending adversarial examples in image classification
Kaleel Mahmood, Phuong Ha Nguyen, Lam M. Nguyen +2
We propose a novel defense against all existing gradient based adversarial attacks on deep neural networks for image classification problems. Our defense is based on a combination…
DTN: A Learning Rate Scheme with Convergence Rate of for SGD
Lam M. Nguyen, Phuong Ha Nguyen, Dzung T. Phan +2
This paper has some inconsistent results, i.e., we made some failed claims because we did some mistakes for using the test criterion for a series. Precisely, our claims on the conv…
Finite-Sum Smooth Optimization with SARAH
Lam M. Nguyen, Marten van Dijk, Dzung T. Phan +3
The total complexity (measured as the total number of gradient computations) of a stochastic first-order optimization algorithm that finds a first-order stationary point of a finit…
New Convergence Aspects of Stochastic Gradient Algorithms
Lam M. Nguyen, Phuong Ha Nguyen, Peter Richtárik +3
The classical convergence analysis of SGD is carried out under the assumption that the norm of the stochastic gradient is uniformly bounded. While this might hold for some loss fun…
Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD
Phuong Ha Nguyen, Lam M. Nguyen, Marten van Dijk
We study the convergence of Stochastic Gradient Descent (SGD) for strongly convex objective functions. We prove for all a lower bound on the expected convergence rate after the…
Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD
Marten van Dijk, Lam M. Nguyen, Phuong Ha Nguyen +1
We study Stochastic Gradient Descent (SGD) with diminishing step sizes for convex objective functions. We introduce a definitional framework and theory that defines and characteriz…
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
Lam M. Nguyen, Phuong Ha Nguyen, Marten van Dijk +3
Stochastic gradient descent (SGD) is the optimization algorithm of choice in many machine learning applications such as regularized empirical risk minimization and training deep ne…
Intrinsically Reliable and Lightweight Physical Obfuscated Keys
Raihan Sayeed Khan, Nadim Kanan, Chenglu Jin +8
Physical Obfuscated Keys (POKs) allow tamper-resistant storage of random keys based on physical disorder. The output bits of current POK designs need to be first corrected due to m…