[HTML][HTML] Toward improved machine learning-based intrusion detection for Internet of Things traffic
S Alkadi, S Al-Ahmadi, MM Ben Ismail - Computers, 2023 - mdpi.com
The rapid development of Internet of Things (IoT) networks has revealed multiple security
issues. On the other hand, machine learning (ML) has proven its efficiency in building …
issues. On the other hand, machine learning (ML) has proven its efficiency in building …
Robustness of specifications and its applications to falsification, parameter mining, and runtime monitoring with s-taliro
Logical specifications have enabled formal methods by carefully describing what is correct,
desired or expected of a given system. They have been widely used in runtime monitoring …
desired or expected of a given system. They have been widely used in runtime monitoring …
Predictive runtime monitoring of vehicle models using Bayesian estimation and reachability analysis
We present a predictive runtime monitoring technique for estimating future vehicle positions
and the probability of collisions with obstacles. Vehicle dynamics model how the position …
and the probability of collisions with obstacles. Vehicle dynamics model how the position …
Exploring the role of simulator fidelity in the safety validation of learning‐enabled autonomous systems
A Baheri - AI Magazine, 2023 - Wiley Online Library
This article presents key insights from the New Faculty Highlights talk given at AAAI 2023,
focusing on the crucial role of fidelity simulators in the safety evaluation of learning‐enabled …
focusing on the crucial role of fidelity simulators in the safety evaluation of learning‐enabled …
Black-Box Safety Validation of Autonomous Systems: A Multi-Fidelity Reinforcement Learning Approach
The increasing use of autonomous and semi-autonomous agents in society has made it
crucial to validate their safety. However, the complex scenarios in which they are used may …
crucial to validate their safety. However, the complex scenarios in which they are used may …
Autonomous systems design: Charting a new discipline
S Saidi, D Ziegenbein, JV Deshmukh… - IEEE Design & …, 2021 - ieeexplore.ieee.org
Autonomous Systems Design: Charting a New Discipline Page 1 8 2168-2364/21©2021 IEEE
Copublished by the IEEE CEDA, IEEE CASS, IEEE SSCS, and TTTC IEEE Design&Test …
Copublished by the IEEE CEDA, IEEE CASS, IEEE SSCS, and TTTC IEEE Design&Test …
[HTML][HTML] Verified reductions for optimization
Numerical and symbolic methods for optimization are used extensively in engineering,
industry, and finance. Various methods are used to reduce problems of interest to ones that …
industry, and finance. Various methods are used to reduce problems of interest to ones that …
Safety in autonomous driving: Can tools offer guarantees?
DJ Fremont… - 2021 58th ACM/IEEE …, 2021 - ieeexplore.ieee.org
Persistent challenges in making autonomous vehicles safe and reliable have hampered
their widespread deployment. We believe that formal methods will play an essential role in …
their widespread deployment. We believe that formal methods will play an essential role in …
Robustness Verification of Deep Reinforcement Learning Based Control Systems Using Reward Martingales
Deep Reinforcement Learning (DRL) has gained prominence as an effective approach for
control systems. However, its practical deployment is impeded by state perturbations that …
control systems. However, its practical deployment is impeded by state perturbations that …
[HTML][HTML] Unbounded-time safety verification of stochastic differential dynamics
In this paper, we propose a method for bounding the probability that a stochastic differential
equation (SDE) system violates a safety specification over the infinite time horizon. SDEs are …
equation (SDE) system violates a safety specification over the infinite time horizon. SDEs are …