Browse Proceedings

Providing safety guarantees for autonomous systems is difficult as these systems operate in complex environments that require the use of learning-enabled components, such as deep neural networks (DNNs) for visual perception. DNNs are hard to ...

Classification neural networks fail to detect inputs that do not fall inside the classes they have been trained for. Runtime monitoring techniques on the neuron activation pattern can be used to detect such inputs. We present an approach for ...

Parametric verification of linear temporal properties for stochastic models requires to compute the satisfaction probability of a certain property as a function of the parameters of the model. Smoothed model checking (smMC) [8] infers the ...

We present a framework for the distributed monitoring of networks of components that coordinate by message-passing, following multiparty session protocols specified as global types. We improve over prior works by (i) supporting components whose ...

We present a method for mining parameters of temporal specifications for signal classification. Given a parametric formula and a set of labeled traces, we find one parameter valuation for each class and use it to instantiate the specification ...

Runtime Verification studies how to check a run of a system against a formal specification, typically expressed in some temporal logic. A monitor must produce a verdict at each step that is sound with respect to the specification. It is often the ...

Temporal logics are widely used in runtime verification as they enable the creation of declarative and compositional specifications. However, their ability to model complex data is limited. One must resort to complicated encoding schemes to ...

Runtime verification (RV) can be used for checking the execution of a system against a formal specification. First-order temporal logic allows expressing constraints on the order of occurrence of events and the data that they carry. We present an ...

Hyperproperties are properties that relate multiple execution traces. Previous work on monitoring hyperproperties focused on synchronous hyperproperties, usually specified in HyperLTL. When monitoring synchronous hyperproperties, all traces are ...

We present a framework for the compositional simulation-based analysis of AI-based autonomous systems for Markovian safety specifications. Our compositional approach allows us to cut down the cost of executing a large number of long-running ...

We present the first decentralized algorithm for detecting predicates over continuous-time signals under partial synchrony. A distributed cyber-physical system (CPS) consists of a network of agents, each of which measures (or computes) a ...

We introduce Tagged C, a novel C variant with built-in tag-based reference monitoring that can be enforced by hardware mechanisms such as the PIPE (Processor Interlocks for Policy Enforcement) processor extension. Tagged C expresses security ...

We introduce Spatial Regular Expressions (SpREs) as a novel querying language for pattern matching over perception streams containing spatial and temporal data. To highlight the capabilities of SpREs, we developed the Strem tool as a matching ...

We investigate the role of ensemble methods in learning runtime monitors for operational design domains of autonomous systems. An operational design domain (ODD) of a system captures the conditions under which we can trust the components of the ...

As AI and machine-learned software are used increasingly for making decisions that affect humans, it is imperative that they remain fair and unbiased in their decisions. To complement design-time bias mitigation measures, runtime verification ...

In the domain of video delivery, industrial software systems that produce multimedia streams are increasingly more complex. To ensure correctness of their behaviors, there is a strong need for verification and validation activities. In particular, ...

We present a novel instrumentation language for BISM, a lightweight bytecode-level instrumentation tool for JVM languages. The new DSL aims to simplify the instrumentation process, making it more accessible to a wider user base. It employs an ...

Runtime verification (RV) is an effective lightweight formal method for improving software’s reliability at runtime. There exist no RV tools specially designed for C++ programs. This paper introduces the first one, i.e., CCMOP, which implements an ...

In online monitoring, a monitor is synthesized from a formal specification, which later runs in tandem with the system under study. In offline monitoring the trace is logged as the system progresses to later do post-mortem analysis after the ...

We present eMOP, a tool for incremental runtime verification (RV) of test executions during software evolution. We previously used RV to find hundreds of bugs in open-source projects by monitoring passing tests against formal specifications of ...$$$$

Video capturing devices with limited storage capacity have become increasingly common in recent years. As a result, there is a growing demand for techniques that can effectively analyze and understand these videos. While existing approaches based ...

Pedestrian detection is an important part of the perception system of autonomous vehicles. Foggy and low-light conditions are quite challenging for pedestrian detection, and several models have been proposed to increase the robustness of ...

Instrumentation is crucial in Runtime Verification because it should ensure that monitors are fed with relevant and accurate information about the executing program under monitoring. While expressive instrumentation is desirable to handle any ...

Deep neural networks (DNNs) are instrumental in realizing complex perception systems. As many of these applications are safety-critical by design, engineering rigor is required to ensure that the functional insufficiency of the DNN-based ...