Search Results for author:
Found 49 papers, 19 papers with code
Recovery from Adversarial Attacks in Cyber-physical Systems: Shallow, Deep and Exploratory Works
Cyber-physical systems (CPS) have experienced rapid growth in recent decades.
Uncertainty in Language Models: Assessment through Rank-Calibration
Language Models (LMs) have shown promising performance in natural language generation.
On the Calibration of Multilingual Question Answering LLMs
We also conduct several ablation experiments to study the effect of language distances, language corpus size, and model size on calibration, and how multilingual models compare with their monolingual counterparts for diverse tasks and languages.
Testing learning-enabled cyber-physical systems with Large-Language Models: A Formal Approach
The integration of machine learning (ML) into cyber-physical systems (CPS) offers significant benefits, including enhanced efficiency, predictive capabilities, real-time responsiveness, and the enabling of autonomous operations.
Repairing Learning-Enabled Controllers While Preserving What Works
However, existing repair techniques do not preserve previously correct behaviors.
PAC Prediction Sets Under Label Shift
We propose a novel algorithm for constructing prediction sets with PAC guarantees in the label shift setting.
Memory-Consistent Neural Networks for Imitation Learning
Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations.
IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning
Upon a new task, IBCL (1) updates a knowledge base in the form of a convex hull of model parameter distributions and (2) obtains particular models to address task trade-off preferences with zero-shot.
Curating Naturally Adversarial Datasets for Learning-Enabled Medical Cyber-Physical Systems
However, ensuring the robustness of these models is vital for building trustworthy AI systems.
Distributionally Robust Statistical Verification with Imprecise Neural Networks
A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems.
A Novel Bayes' Theorem for Upper Probabilities
In their seminal 1990 paper, Wasserman and Kadane establish an upper bound for the Bayes' posterior probability of a measurable set $A$, when the prior lies in a class of probability measures $\mathcal{P}$ and the likelihood is precise.
TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction
To address this challenge, we propose the Trustworthy Retrieval Augmented Question Answering, or $\textit{TRAQ}$, which provides the first end-to-end statistical correctness guarantee for RAG.
IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning
Upon a new task, IBCL (1) updates a knowledge base in the form of a convex hull of model parameter distributions and (2) obtains particular models to address task trade-off preferences with zero-shot.
Detection of Adversarial Physical Attacks in Time-Series Image Data
Nevertheless, DNN models have proven to be vulnerable to adversarial digital and physical attacks.
Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning
We propose a model-free reinforcement learning solution, namely the ASAP-Phi framework, to encourage an agent to fulfill a formal specification ASAP.
Causal Repair of Learning-enabled Cyber-physical Systems
However, given the high diversity and complexity of LECs, it is challenging to encode domain knowledge (e. g., the CPS dynamics) in a scalable actual causality model that could generate useful repair suggestions.
Conformal Prediction Regions for Time Series using Linear Complementarity Programming
In fact, to obtain prediction regions over $T$ time steps with confidence $1-\delta$, {previous works require that each individual prediction region is valid} with confidence $1-\delta/T$.
Using Semantic Information for Defining and Detecting OOD Inputs
This can render the current OOD detectors impermeable to inputs lying outside the training distribution but with the same semantic information (e. g. training class labels).
Take Me Home: Reversing Distribution Shifts using Reinforcement Learning
To aid in our estimates of Wasserstein distance, we employ dimensionality reduction through orthonormal projection.
Credal Bayesian Deep Learning
We show that CBDL is better at quantifying and disentangling different types of uncertainties than single BNNs, ensemble of BNNs, and Bayesian Model Averaging.
Angelic Patches for Improving Third-Party Object Detector Performance
Experiments demonstrate the efficacy of the partial-covering patch in solving the complex bounding box problem.
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions).
Guaranteed Conformance of Neurosymbolic Models to Natural Constraints
Next, using these memories we partition the state space into disjoint subsets and compute bounds that should be respected by the neural network in each subset.
CODiT: Conformal Out-of-Distribution Detection in Time-Series Data
Machine learning models are prone to making incorrect predictions on inputs that are far from the training distribution.
PAC Prediction Sets for Meta-Learning
Uncertainty quantification is a key component of machine learning models targeted at safety-critical systems such as in healthcare or autonomous vehicles.
Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations
Algorithm design of AT and its variants are focused on training models at a specified perturbation strength $\epsilon$ and only using the feedback from the performance of that $\epsilon$-robust model to improve the algorithm.
Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
We propose a new method for classification which can improve robustness to distribution shifts, by combining expert knowledge about the ``high-level" structure of the data with standard classifiers.
PAC-Wrap: Semi-Supervised PAC Anomaly Detection
Anomaly detection is essential for preventing hazardous outcomes for safety-critical applications like autonomous driving.
Towards PAC Multi-Object Detection and Tracking
Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation.
Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates
We formulate expert intervention as allowing the agent to execute option templates before learning an implementation.
iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
We propose the new method iDECODe, leveraging in-distribution equivariance for conformal OOD detection.
Confidence Composition for Monitors of Verification Assumptions
To predict safety violations in a verified system, we propose a three-step confidence composition (CoCo) framework for monitoring verification assumptions.
Mako: Semi-supervised continual learning with minimal labeled data via data programming
This tool achieves similar performance, in terms of per-task accuracy and resistance to catastrophic forgetting, as compared to fully labeled data.
Sequential Covariate Shift Detection Using Classifier Two-Sample Tests
This problem can naturally be solved using a two-sample test--- i. e., test whether the current test distribution of covariates equals the training distribution of covariates.
Detecting OODs as datapoints with High Uncertainty
We demonstrate the difference in the detection ability of these techniques and propose an ensemble approach for detection of OODs as datapoints with high uncertainty (epistemic or aleatoric).
PAC Prediction Sets Under Covariate Shift
Our approach focuses on the setting where there is a covariate shift from the source distribution (where we have labeled training examples) to the target distribution (for which we want to quantify uncertainty).
Improving Neural Network Robustness via Persistency of Excitation
Improving adversarial robustness of neural networks remains a major challenge.
ModelGuard: Runtime Validation of Lipschitz-continuous Models
This paper presents ModelGuard, a sampling-based approach to runtime model validation for Lipschitz-continuous models.
Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs
Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution (OOD) inputs.
Confidence Calibration with Bounded Error Using Transformations
As machine learning techniques become widely adopted in new domains, especially in safety-critical systems such as autonomous vehicles, it is crucial to provide accurate output uncertainty estimation.
Improving Classifier Confidence using Lossy Label-Invariant Transformations
Providing reliable model uncertainty estimates is imperative to enabling robust decision making by autonomous agents and humans alike.
PAC Confidence Predictions for Deep Neural Network Classifiers
In our experiments, we demonstrate that our approach can be used to provide guarantees for state-of-the-art DNNs.
A Skew-Sensitive Evaluation Framework for Imbalanced Data Classification
Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task.
Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation
Our algorithm uses importance weighting to correct for the shift from the training to the real-world distribution.
Real-Time Detectors for Digital and Physical Adversarial Inputs to Perception Systems
To highlight this, we demonstrate the efficiency of the proposed detector on ImageNet, a task that is computationally challenging for the majority of relevant defenses, and on physically attacked traffic signs that may be encountered in real-time autonomy applications.
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i. e., the confidence set for a given input contains the true label with high probability.
Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology.
Verisig: verifying safety properties of hybrid systems with neural network controllers
This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers.
Systems and Control
Resilient Linear Classification: An Approach to Deal with Attacks on Training Data
Specifically, a generic metric is proposed that is tailored to measure resilience of classification algorithms with respect to worst-case tampering of the training data.
