Attacking Byzantine Robust Aggregation in High Dimensions

1 code implementation • 22 Dec 2023 • Sarthak Choudhary, Aashish Kolluri, Prateek Saxena

Designing such aggregators is challenging when dealing with high dimensions.

Scalable Neural Network Training over Distributed Graphs

1 code implementation • 25 Feb 2023 • Aashish Kolluri, Sarthak Choudhary, Bryan Hooi, Prateek Saxena

We present RETEXO, the first framework which eliminates the severe communication bottleneck in distributed GNN training while respecting any given data partitioning configuration.

Node Classification

LPGNet: Link Private Graph Networks for Node Classification

1 code implementation • 6 May 2022 • Aashish Kolluri, Teodora Baluta, Bryan Hooi, Prateek Saxena

In this paper, we present a new neural network architecture called LPGNet for training on graphs with privacy-sensitive edges.

Classification Node Classification

Finding The Greedy, Prodigal, and Suicidal Contracts at Scale

4 code implementations • 16 Feb 2018 • Ivica Nikolic, Aashish Kolluri, Ilya Sergey, Prateek Saxena, Aquinas Hobor

On a subset of3, 759 contracts which we sampled for concrete validation and manual analysis, we reproduce real exploits at a true positive rate of 89%, yielding exploits for3, 686 contracts.

Cryptography and Security