A Constraint Mining Approach to Support Monitoring Cyber-Physical Systems

Krismayer, Thomas; Rabiser, Rick; Grünbacher, Paul

doi:10.1007/978-3-030-21290-2_41

Cited by 8 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is generally infeasible to know all constraints initially due to lack of deep domain knowledge or data, whereas some requirements can only be known after going into the operations due to environmental variability [7]. For example, defining constraints for power system state estimation requires determining confidence on measured data.…”

Section: Constraints Learnermentioning

confidence: 99%

See 1 more Smart Citation

Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense

Dutta,

Al-Shaer,

Chatterjee

2021

Preprint

View full text Add to dashboard Cite

With the increasing system complexity and attack sophistication, the necessity of autonomous cyber defense becomes vivid for cyber and cyber-physical systems (CPSs). Many existing frameworks in the current-state-of-the-art either rely on static models with unrealistic assumptions, or fail to satisfy the system safety and security requirements. In this paper, we present a new hybrid autonomous agent architecture that aims to optimize and verify defense policies of reinforcement learning (RL) by incorporating constraints verification (using satisfiability modulo theory (SMT)) into the agent's decision loop. The incorporation of SMT does not only ensure the satisfiability of safety and security requirements, but also provides constant feedback to steer the RL decision-making toward safe and effective actions. This approach is critically needed for CPSs that exhibit high risk due to safety or security violations. Our evaluation of the presented approach in a simulated CPS environment shows that the agent learns the optimal policy fast and defeats diversified attack strategies in 99% cases.

show abstract

Section: Constraints Learnermentioning

confidence: 99%

“…Though we consider a static value for that required number of events, we plan to determine it dynamically in future extension. Moreover, there are ongoing research efforts to mine such constraints at real-time from observations such as runtime event logs or physical world information [7].…”

Section: Constraints Learnermentioning

confidence: 99%

Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense

Dutta,

Al-Shaer,

Chatterjee

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Step 1: Mining constraints for datasets. The approach then uses constraint mining [8] to extract constraints in an existing DSL [12] for both datasets. This step uses all the constraints produced by the constraint mining algorithm with a confidence of at least 90% (based on initial experiments) to filter irrelevant constraints and therefore does not require user input.…”

Section: Evolution Analysis Approachmentioning

confidence: 99%

“…Our existing constraint mining approach [8] extracts the behavior of a software system by analyzing execution logs collected during system runs. These logs contain complex events consisting of an event type, a timestamp, and (optionally) event data elements, such as sensor values or status messages.…”

Section: Background: Constraint Miningmentioning

confidence: 99%

“…In this paper, we propose a new approach for determining the change impact by applying our existing constraint mining algorithm [8] to analyze the execution logs of multiple software versions. Our mining technique detects and analyzes recurring event patterns to extract constraints on event occurrence, timing, and event data (as well as combinations of these types).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparing Constraints Mined From Execution Logs to Understand Software Evolution

Krismayer¹,

Vierhauser²,

Rabiser³

et al. 2019

2019 IEEE International Conference on Software Maintenance and Evolution (ICSME)

Self Cite

View full text Add to dashboard Cite

Complex software systems evolve frequently, e.g., when introducing new features or fixing bugs during maintenance. However, understanding the impact of such changes on system behavior is often difficult. Many approaches have thus been proposed that analyze systems before and after changes, e.g., by comparing source code, model-based representations, or system execution logs. In this paper, we propose an approach for comparing run-time constraints, synthesized by a constraint mining algorithm, based on execution logs recorded before and after changes. Specifically, automatically mined constraints define the expected timing and order of recurring events and the values of data elements attached to events. Our approach presents the differences of the mined constraints to users, thereby providing a higher-level view on software evolution and supporting the analysis of the impact of changes on system behavior. We present a motivating example and a preliminary evaluation based on a cyber-physical system controlling unmanned aerial vehicles. The results of our preliminary evaluation show that our approach can help to analyze changed behavior and thus contributes to understanding software evolution.

show abstract

Machine Learning and Big Data in Cyber‐Physical System: Methods, Applications and Challenges

Nayak

Kumar²,

Reddy³

et al. 2021

Cognitive Engineering for Next Generation Computing

View full text Add to dashboard Cite

A Constraint Mining Approach to Support Monitoring Cyber-Physical Systems

Cited by 8 publications

References 25 publications

Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense

Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense

Comparing Constraints Mined From Execution Logs to Understand Software Evolution

Machine Learning and Big Data in Cyber‐Physical System: Methods, Applications and Challenges

Contact Info

Product

Resources

About