research
∙
09/01/2023
Curating Naturally Adversarial Datasets for Trustworthy AI in Healthcare
Deep learning models have shown promising predictive accuracy for time-s...
share
research
∙
08/28/2023
Distributionally Robust Statistical Verification with Imprecise Neural Networks
A particularly challenging problem in AI safety is providing guarantees ...
research
∙
07/13/2023
A Novel Bayes' Theorem for Upper Probabilities
In their seminal 1990 paper, Wasserman and Kadane establish an upper bou...
research
∙
07/07/2023
TRAC: Trustworthy Retrieval Augmented Chatbot
Although conversational AIs have demonstrated fantastic performance, the...
research
∙
05/24/2023
Zero-shot Task Preference Addressing Enabled by Imprecise Bayesian Continual Learning
Like generic multi-task learning, continual learning has the nature of m...
research
∙
04/27/2023
Detection of Adversarial Physical Attacks in Time-Series Image Data
Deep neural networks (DNN) have become a common sensing modality in auto...
research
∙
04/25/2023
Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning
We propose a model-free reinforcement learning solution, namely the ASAP...
research
∙
04/06/2023
Causal Repair of Learning-enabled Cyber-physical Systems
Models of actual causality leverage domain knowledge to generate convinc...
research
∙
04/03/2023
Conformal Prediction Regions for Time Series using Linear Complementarity Programming
Conformal prediction is a statistical tool for producing prediction regi...
research
∙
02/21/2023
Using Semantic Information for Defining and Detecting OOD Inputs
As machine learning models continue to achieve impressive performance ac...
research
∙
02/20/2023
Take Me Home: Reversing Distribution Shifts using Reinforcement Learning
Deep neural networks have repeatedly been shown to be non-robust to the ...
research
∙
02/19/2023
Imprecise Bayesian Neural Networks
Uncertainty quantification and robustness to distribution shifts are imp...
research
∙
01/26/2023
Conservative Safety Monitors of Stochastic Dynamical Systems
Generating accurate runtime safety estimates for autonomous systems is v...
research
∙
12/20/2022
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing
Recently it has been shown that state-of-the-art NLP models are vulnerab...
research
∙
12/02/2022
Guaranteed Conformance of Neurosymbolic Models to Natural Constraints
Deep neural networks have emerged as the workhorse for a large section o...
research
∙
10/14/2022
Let's Talk Through Physics! Covert Cyber-Physical Data Exfiltration on Air-Gapped Edge Devices
Although organizations are continuously making concerted efforts to hard...
research
∙
09/09/2022
Learning Enabled Fast Planning and Control in Dynamic Environments with Intermittent Information
This paper addresses a safe planning and control problem for mobile robo...
research
∙
07/24/2022
CODiT: Conformal Out-of-Distribution Detection in Time-Series Data
Machine learning models are prone to making incorrect predictions on inp...
research
∙
07/06/2022
PAC Prediction Sets for Meta-Learning
Uncertainty quantification is a key component of machine learning models...
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 ...
research
∙
06/10/2022
Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
The performance of machine learning models can significantly degrade und...
research
∙
05/22/2022
PAC-Wrap: Semi-Supervised PAC Anomaly Detection
Anomaly detection is essential for preventing hazardous outcomes for saf...
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...
research
∙
04/15/2022
Towards PAC Multi-Object Detection and Tracking
Accurately detecting and tracking multi-objects is important for safety-...
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...
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...
research
∙
11/04/2021
Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis
Autonomous systems with machine learning-based perception can exhibit un...
research
∙
11/03/2021
Confidence Composition for Monitors of Verification Assumptions
Closed-loop verification of cyber-physical systems with neural network c...
research
∙
08/13/2021
Detecting OODs as datapoints with High Uncertainty
Deep neural networks (DNNs) are known to produce incorrect predictions w...
research
∙
06/17/2021
PAC Prediction Sets Under Covariate Shift
An important challenge facing modern machine learning is how to rigorous...
research
∙
06/03/2021
Robust Learning via Persistency of Excitation
Improving adversarial robustness of neural networks remains a major chal...
research
∙
04/30/2021
ModelGuard: Runtime Validation of Lipschitz-continuous Models
This paper presents ModelGuard, a sampling-based approach to runtime mod...
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...
research
∙
02/25/2021
Confidence Calibration with Bounded Error Using Transformations
As machine learning techniques become widely adopted in new domains, esp...
research
∙
11/09/2020
Improving Classifier Confidence using Lossy Label-Invariant Transformations
Providing reliable model uncertainty estimates is imperative to enabling...
research
∙
11/02/2020
PAC Confidence Predictions for Deep Neural Network Classifiers
A key challenge for deploying deep neural networks (DNNs) in safety crit...
research
∙
10/12/2020
Class-Weighted Evaluation Metrics for Imbalanced Data Classification
Class distribution skews in imbalanced datasets may lead to models with ...
research
∙
04/06/2020
Optimal Virtual Cluster-based Multiprocessor Scheduling
Scheduling of constrained deadline sporadic task systems on multiprocess...
research
∙
02/29/2020
Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation
Reliable uncertainty estimates are an important tool for helping autonom...
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...
research
∙
12/31/2019
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
We propose an algorithm combining calibrated prediction and generalizati...
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...
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...
research
∙
06/20/2018
Self-Driving Vehicle Verification Towards a Benchmark
Industrial cyber-physical systems are hybrid systems with strict safety ...
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...
research
∙
08/10/2017