Arjun Nitin Bhagoji

发表

PAC-learning in the presence of adversaries

Prateek Mittal, Daniel Cullina, Arjun Nitin Bhagoji, 2018, NeurIPS.

DARTS: Deceiving Autonomous Cars with Toxic Signs pdf

Prateek Mittal, Mung Chiang, Arjun Nitin Bhagoji, 2018, ArXiv.

Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos pdf

Prateek Mittal, Mung Chiang, Arjun Nitin Bhagoji, 2018, ArXiv.

Lower Bounds on Adversarial Robustness from Optimal Transport

Daniel Cullina, Arjun Nitin Bhagoji, Prateek Mittal, 2019, NeurIPS.

Dimensionality Reduction as a Defense against Evasion Attacks on Machine Learning Classifiers pdf

Prateek Mittal, Daniel Cullina, Arjun Nitin Bhagoji, 2017, ArXiv.

Exploring the Space of Black-box Attacks on Deep Neural Networks pdf

Dawn Xiaodong Song, Bo Li, Arjun Nitin Bhagoji, 2017, ArXiv.

Advances and Open Problems in Federated Learning pdf

Richard Nock, Zaïd Harchaoui, David Evans, 2019, Found. Trends Mach. Learn..

Analyzing Federated Learning through an Adversarial Lens

Prateek Mittal, Arjun Nitin Bhagoji, Seraphin B. Calo, 2018, ICML.

PAC-learning in the presence of evasion adversaries pdf

Prateek Mittal, Daniel Cullina, Arjun Nitin Bhagoji, 2018, NIPS 2018.

Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples pdf

Prateek Mittal, Mung Chiang, Daniel Cullina, 2019, ArXiv.

PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking.

Chong Xiang, Arjun Nitin Bhagoji, Prateek Mittal, 2020 .

Enhancing robustness of machine learning systems via data transformations

Daniel Cullina, Arjun Nitin Bhagoji, Chawin Sitawarin, 2017, 2018 52nd Annual Conference on Information Sciences and Systems (CISS).

Not All Pixels are Born Equal: An Analysis of Evasion Attacks under Locality Constraints

Prateek Mittal, Mung Chiang, Arjun Nitin Bhagoji, 2018, CCS.

Analyzing the Robustness of Open-World Machine Learning

Mung Chiang, Liwei Song, Daniel Cullina, 2019, AISec@CCS.

PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields pdf

Chong Xiang, Arjun Nitin Bhagoji, Prateek Mittal, 2020, ArXiv.

A Critical Evaluation of Open-World Machine Learning pdf

Liwei Song, Arjun Nitin Bhagoji, Prateek Mittal, 2020, ArXiv.

Practical Black-Box Attacks on Deep Neural Networks Using Efficient Query Mechanisms

Dawn Xiaodong Song, Bo Li, Arjun Nitin Bhagoji, 2018, ECCV.

Black-box Attacks on Deep Neural Networks via Gradient Estimation

Dawn Xiaodong Song, Bo Li, Arjun Nitin Bhagoji, 2018, ICLR.

Optimus Prime: Linear Transformations to Secure Machine Learning Systems

Arjun Nitin Bhagoji, A. Bhagoji, 2017 .

Advances and Open Problems in Federated Learning

Richard Nock, Zaïd Harchaoui, Mehdi Bennis, 2021, Found. Trends Mach. Learn..

A Real-time Defense against Website Fingerprinting Attacks pdf

Ben Y. Zhao, Haitao Zheng, Arjun Nitin Bhagoji, 2021, ArXiv.

PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking

Prateek Mittal, Arjun Nitin Bhagoji, Vikash Sehwag, 2020, USENIX Security Symposium.

Patch-based Defenses against Web Fingerprinting Attacks

Ben Y. Zhao, Haitao Zheng, Arjun Nitin Bhagoji, 2021, AISec@CCS.

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries

Prateek Mittal, Daniel Cullina, Arjun Nitin Bhagoji, 2021, ICML.

Traceback of Data Poisoning Attacks in Neural Networks pdf

Ben Y. Zhao, Haitao Zheng, Arjun Nitin Bhagoji, 2021, ArXiv.

On the Local Equivalence of 2D Color Codes and Surface Codes with Applications

Pradeep Kiran Sarvepalli, Arjun Nitin Bhagoji, Arun B. Aloshious, 2018, 1804.00866.

Supplementary : Analyzing Federated Learning through an Adversarial Lens

Prateek Mittal, Arjun Nitin Bhagoji, Seraphin Calo, 2019 .