Alexander Robey

发表

Model-Based Robust Deep Learning

George J. Pappas, Hamed Hassani, Alexander Robey, 2020, ArXiv.

Probable Domain Generalization via Quantile Risk Minimization

George J. Pappas, Julius von Kugelgen, Julius von Kügelgen, 2022, Neural Information Processing Systems.

Probable Domain Generalization via Quantile Risk Minimization

George J. Pappas, Julius von Kügelgen, B. Scholkopf, 2022, ArXiv.

Probabilistically Robust Learning: Balancing Average- and Worst-case Performance

George J. Pappas, Luiz F. O. Chamon, Hamed Hassani, 2022, ICML.

Model-Based Domain Generalization pdf

George J. Pappas, Hamed Hassani, Alexander Robey, 2021, NeurIPS.

On the Sample Complexity of Stability Constrained Imitation Learning

Stephen Tu, N. Matni, Tingnan Zhang, 2021, L4DC.

Closing the Closed-Loop Distribution Shift in Safe Imitation Learning pdf

Nikolai Matni, Stephen Tu, Alexander Robey, 2021, ArXiv.

Model-Based Robust Deep Learning pdf

George J. Pappas, Hamed Hassani, Alexander Robey, 2020, ArXiv.

Do Deep Networks Transfer Invariances Across Classes?

George J. Pappas, Chelsea Finn, Hamed Hassani, 2022, ICLR.

Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations pdf

Nikolai Matni, Stephen Tu, Lars Lindemann, 2021, ArXiv.

Probable Domain Generalization via Quantile Risk Minimization

George J. Pappas, Julius von Kügelgen, B. Schölkopf, 2022, NeurIPS.

Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks

Manfred Morari, George J. Pappas, Hamed Hassani, 2019, NeurIPS.

Learning Robust Hybrid Control Barrier Functions for Uncertain Systems pdf

Nikolai Matni, Stephen Tu, Lars Lindemann, 2021, ADHS.

Learning Control Barrier Functions from Expert Demonstrations

Dimos V. Dimarogonas, Nikolai Matni, Dimos V. Dimarogonas, 2020, 2020 59th IEEE Conference on Decision and Control (CDC).

Provable tradeoffs in adversarially robust classification pdf

Edgar Dobriban, Hamed Hassani, Alexander Robey, 2020, IEEE Transactions on Information Theory.

Adversarial Robustness with Semi-Infinite Constrained Learning pdf

Alejandro Ribeiro, George J. Pappas, Hamed Hassani, 2021, NeurIPS.

DO DEEP NETWORKS TRANSFER INVARIANCES

George J. Pappas, Allan Zhou, Alexander Robey, 2022 .

Toward Certified Robustness Against Real-World Distribution Shifts

N. Matni, C. Pasareanu, Hamed Hassani, 2022, 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).

Probable Domain Generalization via Quantile Risk Minimization

George J. Pappas, Julius von Kügelgen, B. Schölkopf, 2022, NeurIPS.

Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks

George J. Pappas, R. Alur, Hamed Hassani, 2022, 2022 IEEE 61st Conference on Decision and Control (CDC).

Adversarial Training Should Be Cast as a Non-Zero-Sum Game

V. Cevher, Hamed Hassani, Fabian Latorre, 2023, ArXiv.

Learning Hybrid Control Barrier Functions from Data pdf

Dimos V. Dimarogonas, Nikolai Matni, Dimos V. Dimarogonas, 2020, CoRL.

Jailbreaking Black Box Large Language Models in Twenty Queries

Patrick Chao, Alexander Robey, Edgar Dobriban, 2023, ArXiv.

Learning Control Barrier Functions from Expert Demonstrations

Dimos V. Dimarogonas, Stephen Tu, N. Matni, 2020, 2020 59th IEEE Conference on Decision and Control (CDC).

Provable Tradeoffs in Adversarially Robust Classification

Hamed Hassani, Alexander Robey, D. Hong, 2020, IEEE Transactions on Information Theory.

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

Alexander Robey, Jiabao Ji, Shiyu Chang, 2024, 2402.16192.

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Alexander Robey, Hamed Hassani, Eric Wong, 2023, ArXiv.

A Safe Harbor for AI Evaluation and Red Teaming

Alexander Robey, Sayash Kapoor, Ashwin Ramaswami, 2024, ArXiv.

Data-Driven Modeling and Verification of Perception-Based Autonomous Systems

Radoslav Ivanov, Alexander Robey, George J Pappas, 2023, ArXiv.

Zero-shot sampling of adversarial entities in biomedical question answering

Christopher A. Choquette-Choo, Daniel M. Ziegler, Alec Radford, 2024, 2402.10527.