Arjun Nitin Bhagoji
10 papers · 2018–2023 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (15) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (5) π Academic Marathon (5)
π
Renaissance Researcher
(6)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(19)
π
Century Club
(10)
π
Conference Pioneer
Conferences
NIPS (5)
ICML (2)
AISTATS (1)
CVPR (1)
ECCV (1)
Top co-authors
Research topics
Keywords
neural network
(4)
adversarial learning
(4)
adversarial robustness
(3)
sample complexity
(2)
backdoor attack
(2)
model poisoning
(2)
adversarial defense
(2)
federated learning
(2)
adversarial example
(2)
robust optimization
(1)
deep learning
(1)
pac learning
(1)
neural network optimization
(1)
vc dimension
(1)
representation learning
(1)
robust classification
(1)
image classification
(1)
0-1 loss
(1)
adversarial classification
(1)
multi-class classification
(1)
Papers
Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker
NIPS 2023
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
AISTATS 2022
Finding Naturally Occurring Physical Backdoors in Image Datasets
NIPS 2022
Understanding Robust Learning through the Lens of Representation Similarities
NIPS 2022
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
ICML 2021
Backdoor Attacks Against Deep Learning Systems in the Physical World
CVPR 2021
Analyzing Federated Learning through an Adversarial Lens
ICML 2019
Lower Bounds on Adversarial Robustness from Optimal Transport
NIPS 2019
PAC-learning in the presence of adversaries
NIPS 2018
Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms
ECCV 2018