10 citations · 74 across the 31 of their papers we have counts for
32 papers
SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models
Jialiang Fan, Weizhe Xu, Oleg Sokolsky +3
Vision-language-action (VLA) benchmarks measure whether a policy completes a requested manipulation task, but binary success can hide safety violations along the trajectory: a poli…
SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems
Jialiang Fan, Weizhe Xu, Mengyu Liu +3
Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based methods generalize poorly,…
Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios
Vivian Lin, Ramneet Kaur, Yahan Yang +6
The safety of learning-enabled cyber-physical systems is compromised by the well-known vulnerabilities of deep neural networks to out-of-distribution (OOD) inputs. Existing literat…
Conservative Perception Models for Probabilistic Verification
Matthew Cleaveland, Pengyuan Lu, Oleg Sokolsky +2
Verifying the behaviors of autonomous systems with learned perception components is a challenging problem due to the complexity of the perception and the uncertainty of operating e…
AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
Xiayan Ji, Anton Xue, Eric Wong +2
Anomaly detection is widely used for identifying critical errors and suspicious behaviors, but current methods lack interpretability. We leverage common properties of existing meth…
Automating Weak Label Generation for Data Programming with Clinicians in the Loop
Jean Park, Sydney Pugh, Kaustubh Sridhar +7
Large Deep Neural Networks (DNNs) are often data hungry and need high-quality labeled data in copious amounts for learning to converge. This is a challenge in the field of medicine…
Recovery from Adversarial Attacks in Cyber-physical Systems: Shallow, Deep and Exploratory Works
Pengyuan Lu, Lin Zhang, Mengyu Liu +4
Cyber-physical systems (CPS) have experienced rapid growth in recent decades. However, like any other computer-based systems, malicious attacks evolve mutually, driving CPS to unde…
Testing learning-enabled cyber-physical systems with Large-Language Models: A Formal Approach
Xi Zheng, Aloysius K. Mok, Ruzica Piskac +5
The integration of machine learning (ML) into cyber-physical systems (CPS) offers significant benefits, including enhanced efficiency, predictive capabilities, real-time responsive…
Repairing Learning-Enabled Controllers While Preserving What Works
Pengyuan Lu, Matthew Cleaveland, Oleg Sokolsky +2
Learning-enabled controllers have been adopted in various cyber-physical systems (CPS). When a learning-enabled controller fails to accomplish its task from a set of initial states…
Distributionally Robust Statistical Verification with Imprecise Neural Networks
Souradeep Dutta, Michele Caprio, Vivian Lin +5
A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems. Verification approaches centered around reachability…
Causal Repair of Learning-enabled Cyber-physical Systems
Pengyuan Lu, Ivan Ruchkin, Matthew Cleaveland +2
Models of actual causality leverage domain knowledge to generate convincing diagnoses of events that caused an outcome. It is promising to apply these models to diagnose and repair…
Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning
Mengyu Liu, Pengyuan Lu, Xin Chen +3
We propose a model-free reinforcement learning solution, namely the ASAP-Phi framework, to encourage an agent to fulfill a formal specification ASAP. The framework leverages a piec…
Using Semantic Information for Defining and Detecting OOD Inputs
Ramneet Kaur, Xiayan Ji, Souradeep Dutta +5
As machine learning models continue to achieve impressive performance across different tasks, the importance of effective anomaly detection for such models has increased as well. I…
DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models
Vivian Lin, Kuk Jin Jang, Souradeep Dutta +3
Deep neural networks have repeatedly been shown to be non-robust to the uncertainties of the real world, even to naturally occurring ones. A vast majority of current approaches hav…
Credal Bayesian Deep Learning
Michele Caprio, Souradeep Dutta, Kuk Jin Jang +4
Uncertainty quantification and robustness to distribution shifts are important goals in machine learning and artificial intelligence. Although Bayesian Neural Networks (BNNs) allow…
Conservative Safety Monitors of Stochastic Dynamical Systems
Matthew Cleaveland, Oleg Sokolsky, Insup Lee +1
Generating accurate runtime safety estimates for autonomous systems is vital to ensuring their continued proliferation. However, exhaustive reasoning about future behaviors is gene…
Let's Talk Through Physics! Covert Cyber-Physical Data Exfiltration on Air-Gapped Edge Devices
Matthew Chan, Nathaniel Snyder, Marcus Lucas +7
Although organizations are continuously making concerted efforts to harden their systems against network attacks by air-gapping critical systems, attackers continuously adapt and u…
CODiT: Conformal Out-of-Distribution Detection in Time-Series Data
Ramneet Kaur, Kaustubh Sridhar, Sangdon Park +4
Machine learning models are prone to making incorrect predictions on inputs that are far from the training distribution. This hinders their deployment in safety-critical applicatio…
PAC-Wrap: Semi-Supervised PAC Anomaly Detection
Shuo Li, Xiayan Ji, Edgar Dobriban +2
Anomaly detection is essential for preventing hazardous outcomes for safety-critical applications like autonomous driving. Given their safety-criticality, these applications benefi…
Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations
Kaustubh Sridhar, Souradeep Dutta, Ramneet Kaur +3
Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few year…
A Framework for Checkpointing and Recovery of Hierarchical Cyber-Physical Systems
Kaustubh Sridhar, Radoslav Ivanov, Vuk Lesi +6
This paper tackles the problem of making complex resource-constrained cyber-physical systems (CPS) resilient to sensor anomalies. In particular, we present a framework for checkpoi…
iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
Ramneet Kaur, Susmit Jha, Anirban Roy +4
Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence…
Confidence Composition for Monitors of Verification Assumptions
Ivan Ruchkin, Matthew Cleaveland, Radoslav Ivanov +4
Closed-loop verification of cyber-physical systems with neural network controllers offers strong safety guarantees under certain assumptions. It is, however, difficult to determine…
Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis
Matthew Cleaveland, Ivan Ruchkin, Oleg Sokolsky +1
Autonomous systems with machine learning-based perception can exhibit unpredictable behaviors that are difficult to quantify, let alone verify. Such behaviors are convenient to cap…