Resilient machine learning for networked cyber physical systems: A survey for machine learning security to securing machine learning for CPS
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 …
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
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 …
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
Abstract The integration of Deep Learning (DL) algorithms in Autonomous Vehicles (AVs)
has revolutionized their precision in navigating various driving scenarios, ranging from anti …
has revolutionized their precision in navigating various driving scenarios, ranging from anti …
{GhostImage}: Remote perception attacks against camera-based image classification systems
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 …
then objects are detected and classified for decision-making purposes; eg, to maneuver an …
Real-time detection of deception attacks in cyber-physical systems
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 …
physical systems (CPS). Detection of such attacks needs to consider time-series sequences …
Detecting one-pixel attacks using variational autoencoders
In the field of medical imaging, artificial intelligence solutions are used for diagnosis,
prediction and treatment processes. Such solutions are vulnerable to cyberattacks …
prediction and treatment processes. Such solutions are vulnerable to cyberattacks …
Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering
Generative models lack rigorous statistical guarantees for their outputs and are therefore
unreliable in safety-critical applications. In this work, we propose Sequential Conformal …
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
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 …
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 …
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
Cyber-physical systems (CPSs) use learning-enabled components (LECs) extensively to
cope with various complex tasks under high-uncertainty environments. However, the dataset …
cope with various complex tasks under high-uncertainty environments. However, the dataset …