Resilient machine learning for networked cyber physical systems: A survey for machine learning security to securing machine learning for CPS

FO Olowononi, DB Rawat, C Liu - … Communications Surveys & …, 2020 - ieeexplore.ieee.org
Cyber Physical Systems (CPS) are characterized by their ability to integrate the physical and
information or cyber worlds. Their deployment in critical infrastructure have demonstrated a …

Functionality-preserving adversarial machine learning for robust classification in cybersecurity and intrusion detection domains: A survey

A McCarthy, E Ghadafi, P Andriotis, P Legg - Journal of Cybersecurity …, 2022 - mdpi.com
Machine learning has become widely adopted as a strategy for dealing with a variety of
cybersecurity issues, ranging from insider threat detection to intrusion and malware …

Deep learning adversarial attacks and defenses in autonomous vehicles: a systematic literature review from a safety perspective

ADM Ibrahum, M Hussain, JE Hong - Artificial Intelligence Review, 2025 - Springer
Abstract The integration of Deep Learning (DL) algorithms in Autonomous Vehicles (AVs)
has revolutionized their precision in navigating various driving scenarios, ranging from anti …

{GhostImage}: Remote perception attacks against camera-based image classification systems

Y Man, M Li, R Gerdes - 23rd International Symposium on Research in …, 2020 - usenix.org
In vision-based object classification systems imaging sensors perceive the environment and
then objects are detected and classified for decision-making purposes; eg, to maneuver an …

Real-time detection of deception attacks in cyber-physical systems

F Cai, X Koutsoukos - International Journal of Information Security, 2023 - Springer
Detection of deception attacks is pivotal to ensure the safe and reliable operation of cyber-
physical systems (CPS). Detection of such attacks needs to consider time-series sequences …

Detecting one-pixel attacks using variational autoencoders

J Alatalo, T Sipola, T Kokkonen - World Conference on Information …, 2022 - Springer
In the field of medical imaging, artificial intelligence solutions are used for diagnosis,
prediction and treatment processes. Such solutions are vulnerable to cyberattacks …

Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering

KR Kladny, B Schölkopf, M Muehlebach - arxiv preprint arxiv:2410.01660, 2024 - arxiv.org
Generative models lack rigorous statistical guarantees for their outputs and are therefore
unreliable in safety-critical applications. In this work, we propose Sequential Conformal …

Scalable Surrogate Verification of Image-based Neural Network Control Systems using Composition and Unrolling

F Cai, C Fan, S Bak - arxiv preprint arxiv:2405.18554, 2024 - arxiv.org
Verifying safety of neural network control systems that use images as input is a difficult
problem because, from a given system state, there is no known way to mathematically model …

Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data

G Song, D Fu, Z Qiu, J Meng, D Zhang - arxiv preprint arxiv:2409.07942, 2024 - arxiv.org
Uncertainty estimation is crucial in scientific data for machine learning. Current uncertainty
estimation methods mainly focus on the model's inherent uncertainty, while neglecting the …

Detection of dataset shifts in learning-enabled cyber-physical systems using variational autoencoder for regression

F Cai, AI Ozdagli, X Koutsoukos - 2021 4th IEEE International …, 2021 - ieeexplore.ieee.org
Cyber-physical systems (CPSs) use learning-enabled components (LECs) extensively to
cope with various complex tasks under high-uncertainty environments. However, the dataset …