Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints

no code implementations • 15 Jun 2022 • Justin Whitehouse, Zhiwei Steven Wu, Aaditya Ramdas, Ryan Rogers

In this work, we generalize noise reduction to the setting of Gaussian noise, introducing the Brownian mechanism.

Fully Adaptive Composition in Differential Privacy

no code implementations • 10 Mar 2022 • Justin Whitehouse, Aaditya Ramdas, Ryan Rogers, Zhiwei Steven Wu

However, these results require that the privacy parameters of all algorithms be fixed before interacting with the data.

Efficient Formal Safety Analysis of Neural Networks

2 code implementations • NeurIPS 2018 • Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana

Our approach can check different safety properties and find concrete counterexamples for networks that are 10$\times$ larger than the ones supported by existing analysis techniques.

Adversarial Attack Adversarial Defense +3

Formal Security Analysis of Neural Networks using Symbolic Intervals

3 code implementations • 28 Apr 2018 • Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana

In this paper, we present a new direction for formally checking security properties of DNNs without using SMT solvers.

Autonomous Vehicles Collision Avoidance