Related papers: From Points to Sets: Set-Based Safety Verification…

Pose-based Video Anomaly Detection (VAD) has gained significant attention for its privacy-preserving nature and robustness to environmental variations. However, traditional frame-level evaluations treat video as a collection of isolated…

Many safety-critical control systems must operate under latent uncertainty that sensors cannot directly resolve at decision time. Such uncertainty, arising from unknown physical properties, exogenous disturbances, or unobserved environment…

A fundamental and classical problem in mobile autonomous systems is maintaining the safety of autonomous agents during deployment. Prior literature has presented techniques using control barrier functions (CBFs) to achieve this goal. These…

Camera-based adaptive traffic signal control is inherently partially observable: detections can be missed, vehicle speeds and distances can be noisy, and a phase-change decision becomes temporally irreversible once yellow onset is…

We study the safety verification problem for a class of distributed parameter systems described by partial differential equations (PDEs), i.e., the problem of checking whether the solutions of the PDE satisfy a set of constraints at a…

Level set estimation (LSE), the problem of identifying the set of input points where a function takes value above (or below) a given threshold, is important in practical applications. When the function is expensive-to-evaluate and…

Continuous monitoring of trained ML models to determine when their predictions should and should not be trusted is essential for their safe deployment. Such a framework ought to be high-performing, explainable, post-hoc and actionable. We…

Current safety alignment methods encode safe behavior implicitly within model parameters, creating a fundamental opacity: we cannot easily inspect why a model refuses a request, nor intervene when its safety judgments fail. We propose Safe…

Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a…

Recent works have shown that foundational safe control methods, such as Hamilton-Jacobi (HJ) reachability analysis, can be applied in the latent space of world models. While this enables the synthesis of latent safety filters for…

This paper provides a bound on the number of numeric operations (fixed or floating point) that can safely be performed before accuracy is lost. This work has important implications for control systems with safety-critical software, as these…

Accurate perception, state estimation and mapping are essential for safe robotic navigation as planners and controllers rely on these components for safety-critical decisions. However, existing mapping approaches often assume perfect pose…

Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks. However, lacking…

Real-time safety metrics are important for the automated driving system (ADS) to assess the risk of driving situations and to assist the decision-making. Although a number of real-time safety metrics have been proposed in the literature,…

In this paper, we consider a multi-objective control problem for stochastic systems that seeks to minimize a cost of interest while ensuring safety. We introduce a novel measure of safety risk using the conditional value-at-risk and a set…

A barrier certificate is an inductive invariant function which can be used for the safety verification of a hybrid system. Safety verification based on barrier certificate has the benefit of avoiding explicit computation of the exact…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

This paper presents a new algorithm for set-based state estimation of nonlinear discrete-time systems with bounded uncertainties. The novel method builds upon essential properties and computational advantages of constrained zonotopes (CZs)…

In this paper we seek to quantify the ability of learning to improve safety guarantees endowed by Control Barrier Functions (CBFs). In particular, we investigate how model uncertainty in the time derivative of a CBF can be reduced via…

Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization of key anatomical structures, reasoning about their geometric relationships to one another, and determining the quality…