Somesh Jha
Artificial Intelligence · 2000–2019
A researcher in the Science corpus: 33 papers; trusts 454 researchers and is trusted by 1,090 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 506 citations into it; #991 of 36,961 by trust here, #435 by citations
- Privacy & Security — 244 citations into it; #66 of 710 by trust here, #31 by citations
- Safety, Robustness & Interpretability — 119 citations into it; #17 of 2,259 by trust here, #12 by citations
- Computer Networks and Communications — 104 citations into it; #674 of 9,996 by trust here, #1,107 by citations
- Signal Processing — 94 citations into it; #338 of 7,592 by trust here, #135 by citations
- Information Systems — 88 citations into it; #2,336 of 9,233 by trust here, #2,343 by citations
- Computational Theory and Mathematics — 66 citations into it; #4,866 of 12,489 by trust here, #2,253 by citations
- Statistics and Probability — 62 citations into it; #4,363 of 13,188 by trust here, #3,220 by citations
Whom Somesh Jha trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- Yann LeCun
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Raef Bassily
- Ú. Erlingsson
- Diederik P. Kingma
- Ian J. Goodfellow
- Christian Szegedy
Who trusts Somesh Jha overall
- Nicolas Papernot
- Nicholas Carlini
- Patrick Drew McDaniel
- Jinyuan Jia
- Florian Tramèr
- Ian J. Goodfellow
- Reza Shokri
- Ziqi Yang
- Liwei Song
- Tianhao Wang
Papers from Somesh Jha's perspective
Ordered by how strongly the researchers Somesh Jha trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks (2015) — 3,315 citations
- Practical Black-Box Attacks against Machine Learning (2016) — 4,113 citations
- The Limitations of Deep Learning in Adversarial Settings (2015) — 4,317 citations
- Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples (2016) — 496 citations
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (2015) — 3,376 citations
- Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting (2017) — 1,558 citations
- The Unintended Consequences of Overfitting: Training Data Inference Attacks (2017) — 41 citations
- Privacy-Preserving Ridge Regression with only Linearly-Homomorphic Encryption (2018) — 103 citations
- A Methodology for Formalizing Model-Inversion Attacks (2016) — 191 citations
- Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics (2016) — 239 citations
- Modular verification of software components in C (2003) — 554 citations
- Automated generation and analysis of attack graphs (2002) — 1,458 citations
- Counterexample-guided abstraction refinement for symbolic model checking (2003) — 1,114 citations
- Locally Differentially Private Protocols for Frequency Estimation (2017) — 650 citations
- Privacy at Scale: Local Differential Privacy in Practice (2018) — 307 citations
- Answering Multi-Dimensional Analytical Queries under Local Differential Privacy (2019) — 109 citations
- Practical and Robust Privacy Amplification with Multi-Party Differential Privacy (2019) — 11 citations
- Outis: Crypto-Assisted Differential Privacy on Untrusted Servers (2019) — 9 citations
- Cryptϵ: Crypto-Assisted Differential Privacy on Untrusted Servers (2019) — 103 citations
- Improving utility and security of the shuffler-based differential privacy (2019) — 40 citations