b'Insup Lee'

research

∙ 06/13/2022

Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations

Adversarial training (AT) and its variants have spearheaded progress in ...

Kaustubh Sridhar, et al. ∙

research

∙ 06/10/2022

Memory Classifiers: Two-stage Classification for Robustness in Machine Learning

The performance of machine learning models can significantly degrade und...

Souradeep Dutta, et al. ∙

research

∙ 05/22/2022

PAC-Wrap: Semi-Supervised PAC Anomaly Detection

Anomaly detection is essential for preventing hazardous outcomes for saf...

Shuo Li, et al. ∙

research

∙ 05/17/2022

A Framework for Checkpointing and Recovery of Hierarchical Cyber-Physical Systems

This paper tackles the problem of making complex resource-constrained cy...

Kaustubh Sridhar, et al. ∙

research

∙ 04/15/2022

Towards PAC Multi-Object Detection and Tracking

Accurately detecting and tracking multi-objects is important for safety-...

Shuo Li, et al. ∙

research

∙ 02/25/2022

Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates

Environments with sparse rewards and long horizons pose a significant ch...

Souradeep Dutta, et al. ∙

research

∙ 01/07/2022

iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection

Machine learning methods such as deep neural networks (DNNs), despite th...

Ramneet Kaur, et al. ∙

research

∙ 11/04/2021

Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis

Autonomous systems with machine learning-based perception can exhibit un...

Matthew Cleaveland, et al. ∙

research

∙ 11/03/2021

Confidence Composition for Monitors of Verification Assumptions

Closed-loop verification of cyber-physical systems with neural network c...

Ivan Ruchkin, et al. ∙

research

∙ 08/13/2021

Detecting OODs as datapoints with High Uncertainty

Deep neural networks (DNNs) are known to produce incorrect predictions w...

Ramneet Kaur, et al. ∙

research

∙ 06/17/2021

PAC Prediction Sets Under Covariate Shift

An important challenge facing modern machine learning is how to rigorous...

Sangdon Park, et al. ∙

research

∙ 06/03/2021

Robust Learning via Persistency of Excitation

Improving adversarial robustness of neural networks remains a major chal...

Kaustubh Sridhar, et al. ∙

research

∙ 04/30/2021

ModelGuard: Runtime Validation of Lipschitz-continuous Models

This paper presents ModelGuard, a sampling-based approach to runtime mod...

Taylor J. Carpenter, et al. ∙

research

∙ 03/23/2021

Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs

Deep neural networks (DNNs) are known to produce incorrect predictions w...

Ramneet Kaur, et al. ∙

research

∙ 02/25/2021

Confidence Calibration with Bounded Error Using Transformations

As machine learning techniques become widely adopted in new domains, esp...

Sooyong Jang, et al. ∙

research

∙ 11/09/2020

Improving Classifier Confidence using Lossy Label-Invariant Transformations

Providing reliable model uncertainty estimates is imperative to enabling...

Sooyong Jang, et al. ∙

research

∙ 11/02/2020

PAC Confidence Predictions for Deep Neural Network Classifiers

A key challenge for deploying deep neural networks (DNNs) in safety crit...

Sangdon Park, et al. ∙

research

∙ 10/12/2020

Class-Weighted Evaluation Metrics for Imbalanced Data Classification

Class distribution skews in imbalanced datasets may lead to models with ...

Akhilesh Gupta, et al. ∙

research

∙ 04/06/2020

Optimal Virtual Cluster-based Multiprocessor Scheduling

Scheduling of constrained deadline sporadic task systems on multiprocess...

Arvind Easwaran, et al. ∙

research

∙ 02/29/2020

Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation

Reliable uncertainty estimates are an important tool for helping autonom...

Sangdon Park, et al. ∙

research

∙ 02/23/2020

VisionGuard: Runtime Detection of Adversarial Inputs to Perception Systems

Deep neural network (DNN) models have proven to be vulnerable to adversa...

Yiannis Kantaros, et al. ∙

research

∙ 12/31/2019

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction

We propose an algorithm combining calibrated prediction and generalizati...

Sangdon Park, et al. ∙

research

∙ 10/24/2019

Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller

This paper describes a verification case study on an autonomous racing c...

Radoslav Ivanov, et al. ∙

research

∙ 09/11/2019

Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees

Reinforcement Learning (RL) has emerged as an efficient method of choice...

Mohammadhosein Hasanbeig, et al. ∙

research

∙ 06/20/2018

Self-Driving Vehicle Verification Towards a Benchmark

Industrial cyber-physical systems are hybrid systems with strict safety ...

Nima Roohi, et al. ∙

research

∙ 06/20/2018

Injected and Delivered: Fabricating Implicit Control over Actuation Systems by Spoofing Inertial Sensors

Inertial sensors provide crucial feedback for control systems to determi...

Yazhou Tu, et al. ∙

research

∙ 08/10/2017

Resilient Linear Classification: An Approach to Deal with Attacks on Training Data

Data-driven techniques are used in cyber-physical systems (CPS) for cont...

Sangdon Park, et al. ∙

Insup Lee

Featured Co-authors

George J. Pappas

Osbert Bastani

Shuo Li

Alessandro Abate

Daniel Kroening

Arvind Easwaran

Nikolai Matni

Edgar Dobriban

Justin Gottschlich

Susmit Jha

Ryan Marcus

Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations

Memory Classifiers: Two-stage Classification for Robustness in Machine Learning

PAC-Wrap: Semi-Supervised PAC Anomaly Detection

A Framework for Checkpointing and Recovery of Hierarchical Cyber-Physical Systems

Towards PAC Multi-Object Detection and Tracking

Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates

iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection

Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis

Confidence Composition for Monitors of Verification Assumptions

Detecting OODs as datapoints with High Uncertainty

PAC Prediction Sets Under Covariate Shift

Robust Learning via Persistency of Excitation

ModelGuard: Runtime Validation of Lipschitz-continuous Models

Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs

Confidence Calibration with Bounded Error Using Transformations

Improving Classifier Confidence using Lossy Label-Invariant Transformations

PAC Confidence Predictions for Deep Neural Network Classifiers

Class-Weighted Evaluation Metrics for Imbalanced Data Classification

Optimal Virtual Cluster-based Multiprocessor Scheduling

Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation

VisionGuard: Runtime Detection of Adversarial Inputs to Perception Systems

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction

Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller

Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees

Self-Driving Vehicle Verification Towards a Benchmark

Injected and Delivered: Fabricating Implicit Control over Actuation Systems by Spoofing Inertial Sensors

Resilient Linear Classification: An Approach to Deal with Attacks on Training Data