Related papers: Vision-Based Runtime Monitoring under Varying Spec…

Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as \emph{text-only} controllers under partial observability --…

The software architecture behind modern autonomous vehicles (AV) is becoming more complex steadily. Safety verification is now an imminent task prior to the large-scale deployment of such convoluted models. For safety-critical tasks in…

Real-world autonomous driving must adhere to complex human social rules that extend beyond legally codified traffic regulations. Many of these semantic constraints, such as yielding to emergency vehicles, complying with traffic officers'…

We propose a signal temporal logic (STL)-based framework that rigorously verifies the feasibility of a mission described in STL and synthesizes control to safely execute it. The proposed framework ensures safe and reliable operation through…

Predictive maintenance in complex systems is often complicated by the heterogeneity and redundancy of monitored variables,which can obscure fault-relevant information and reduce model interpretability. This work proposes a semantic feature…

This work focuses on the persistent monitoring problem, where a set of targets moving based on an unknown model must be monitored by an autonomous mobile robot with a limited sensing range. To keep each target's position estimate as…

This study carries forward the line of enquiry that seeks to characterize precisely which security policies are enforceable by runtime monitors. In this regard, Basin et al.\ recently refined the structure that helps distinguish between…

Reliable fall detection in elderly care requires monitoring systems that are not only accurate but also capable of producing stable, interpretable explanations of motion dynamics, a requirement that existing post hoc explainability methods…

Tracking points in videos is typically formulated as frame-to-frame correspondence, where each point is matched locally to the next frame. While this works over short horizons, errors accumulate under articulation, occlusion, and viewpoint…

There is an emerging trend in applying deep learning methods to control complex nonlinear systems. This paper considers enhancing the runtime safety of nonlinear systems controlled by neural networks in the presence of disturbance and…

LTL3 is a multi-valued variant of Linear-time Temporal Logic for runtime verification applications. The semantic descriptions of LTL3 in previous work are given only in terms of the relationship to conventional LTL. Our approach, by…

Fine-tuning pretrained language models can improve task performance while subtly altering the evidence a model relies on. We propose a training-time interpretability view that tracks token-level attributions across finetuning epochs. We…

Not all properties are monitorable. This is a well-known fact, and it means there exist properties that cannot be fully verified at runtime. However, given a non-monitorable property, a monitor can still be synthesised, but it could end up…

In this paper, we provide a Dynamic Programming algorithm for on-line monitoring of the state robustness of Metric Temporal Logic specifications with past time operators. We compute the robustness of MTL with unbounded past and bounded…

Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and…

The main purpose of this paper is to introduce a first-order temporal logic, LTLFO, and a corresponding monitor construction based on a new type of automaton, called spawning automaton. Specifically, we show that monitoring a specification…

Online monitoring aims to evaluate or to predict, at runtime, whether or not the behaviors of a system satisfy some desired specification. It plays a key role in safety-critical cyber-physical systems. In this work, we propose a new…

Adversarial robustness verification is essential for ensuring the safe deployment of Large Language Models (LLMs) in runtime-critical applications. However, formal verification techniques remain computationally infeasible for modern LLMs…

Dynamic systems in AI are often complex and heterogeneous, so that an internal specification is not accessible and verification techniques such as model checking are not applicable. Monitoring is in such cases an attractive alternative, as…

Predicting the minimum operating voltage ($V_{min}$) of chips is one of the important techniques for improving the manufacturing testing flow, as well as ensuring the long-term reliability and safety of in-field systems. Current $V_{min}$…