activity
20182022
most citedReluDiff: Differential Verification of Deep Neural Networks

49 citations · 57 across the 5 of their papers we have counts for

collaborators

12 papers

cs.LG2022

LinSyn: Synthesizing Tight Linear Bounds for Arbitrary Neural Network Activation Functions

Brandon Paulsen, Chao Wang

The most scalable approaches to certifying neural network robustness depend on computing sound linear lower and upper bounds for the network's activation functions. Current approac…

cs.SE20211 cited

Data-Driven Synthesis of Provably Sound Side Channel Analyses

Jingbo Wang, Chungha Sung, Mukund Raghothaman +1

We propose a data-driven method for synthesizing a static analyzer to detect side-channel information leaks in cryptographic software. Compared to the conventional way of manually…

cs.LG20204 cited

NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximation

Brandon Paulsen, Jingbo Wang, Jiawei Wang +1

As neural networks make their way into safety-critical systems, where misbehavior can lead to catastrophes, there is a growing interest in certifying the equivalence of two structu…

cs.LG2020

DiffRNN: Differential Verification of Recurrent Neural Networks

Sara Mohammadinejad, Brandon Paulsen, Chao Wang +1

Recurrent neural networks (RNNs) such as Long Short Term Memory (LSTM) networks have become popular in a variety of applications such as image processing, data classification, spee…

cs.LG202049 cited

ReluDiff: Differential Verification of Deep Neural Networks

Brandon Paulsen, Jingbo Wang, Chao Wang

As deep neural networks are increasingly being deployed in practice, their efficiency has become an important issue. While there are compression techniques for reducing the network…

cs.CR2019

Debreach: Mitigating Compression Side Channels via Static Analysis and Transformation

Brandon Paulsen, Chungha Sung, Peter A. H. Peterson +1

Compression is an emerging source of exploitable side-channel leakage that threatens data security, particularly in web applications where compression is indispensable for performa…