Search Results for author: Prateek Saxena

Found 10 papers, 8 papers with code

Attacking Byzantine Robust Aggregation in High Dimensions

1 code implementation22 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 implementation25 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

Membership Inference Attacks and Generalization: A Causal Perspective

1 code implementation18 Sep 2022 Teodora Baluta, Shiqi Shen, S. Hitarth, Shruti Tople, Prateek Saxena

Our causal models also show a new connection between generalization and MI attacks via their shared causal factors.

LPGNet: Link Private Graph Networks for Node Classification

1 code implementation6 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

EPIE Dataset: A Corpus For Possible Idiomatic Expressions

1 code implementation16 Jun 2020 Prateek Saxena, Soma Paul

Idiomatic expressions have always been a bottleneck for language comprehension and natural language understanding, specifically for tasks like Machine Translation(MT).

Machine Translation Natural Language Understanding

Scalable Quantitative Verification For Deep Neural Networks

no code implementations17 Feb 2020 Teodora Baluta, Zheng Leong Chua, Kuldeep S. Meel, Prateek Saxena

But these existing techniques provide either scalability to large networks or formal guarantees, not both.

Adversarial Robustness

Practical Verifiable In-network Filtering for DDoS defense

1 code implementation4 Jan 2019 Deli Gong, Muoi Tran, Shweta Shinde, Hao Jin, Vyas Sekar, Prateek Saxena, Min Suk Kang

In this paper, we show the technical feasibility of verifiable in-network filtering, called VIF, that offers filtering verifiability to DDoS victims and neighbor ASes.

Cryptography and Security

OHIE: Blockchain Scaling Made Simple

1 code implementation30 Nov 2018 Haifeng Yu, Ivica Nikolic, Ruomu Hou, Prateek Saxena

Many blockchain consensus protocols have been proposed recently to scale the throughput of a blockchain with available bandwidth.

Distributed, Parallel, and Cluster Computing

Finding The Greedy, Prodigal, and Suicidal Contracts at Scale

4 code implementations16 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

Cannot find the paper you are looking for? You can Submit a new open access paper.