Cover Image

Hyperproperty-Constrained Secure Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bonnah, Ernest, Nguyen, Luan Viet, Hoque, Khaza Anuarul
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning Logic in Computer Science Systems and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TOGGLE: Temporal Logic-Guided Large Language Model Compression for Edge
by: Khalil, Khurram, et al.
Published: (2025)

Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach
by: Sharifi, Iman, et al.
Published: (2023)

NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic
by: Quansah, Paapa Kwesi, et al.
Published: (2026)

1-2-3-Go! Policy Synthesis for Parameterized Markov Decision Processes via Decision-Tree Learning and Generalization
by: Azeem, Muqsit, et al.
Published: (2024)

EPSILON: Adaptive Fault Mitigation in Approximate Deep Neural Network using Statistical Signatures
by: Khalil, Khurram, et al.
Published: (2025)

Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision
by: Teuber, Samuel, et al.
Published: (2025)

Verification of Autonomous Neural Car Control with KeYmaera X
by: Prebet, Enguerrand, et al.
Published: (2025)

Neural Proofs for Sound Verification and Control of Complex Systems
by: Abate, Alessandro
Published: (2025)

Provably Safe Neural Network Controllers via Differential Dynamic Logic
by: Teuber, Samuel, et al.
Published: (2024)

Efficient Shield Synthesis via State-Space Transformation
by: Brorholt, Asger Horn, et al.
Published: (2024)

k-Inductive Neural Barrier Certificates for Unknown Nonlinear Dynamics
by: Wooding, Ben, et al.
Published: (2026)

Monitoring Second-Order Hyperproperties
by: Beutner, Raven, et al.
Published: (2024)

RIFT: A Scalable Methodology for LLM Accelerator Fault Assessment using Reinforcement Learning
by: Khalil, Khurram, et al.
Published: (2025)

Efficient Dynamic Shielding for Parametric Safety Specifications
by: Corsi, Davide, et al.
Published: (2025)

Strategy Logic, Imperfect Information, and Hyperproperties
by: Beutner, Raven, et al.
Published: (2025)

HypRL: Reinforcement Learning of Control Policies for Hyperproperties
by: Hsu, Tzu-Han, et al.
Published: (2025)

On Alternating-Time Temporal Logic, Hyperproperties, and Strategy Sharing
by: Beutner, Raven, et al.
Published: (2023)

Taming Silent Failures: A Framework for Verifiable AI Reliability
by: Yang, Guan-Yan, et al.
Published: (2025)

Tolerance of Reinforcement Learning Controllers against Deviations in Cyber Physical Systems
by: Zhang, Changjian, et al.
Published: (2024)

Learning Algorithms for Verification of Markov Decision Processes
by: Brázdil, Tomáš, et al.
Published: (2024)

Safe and Reliable Training of Learning-Based Aerospace Controllers
by: Mandal, Udayan, et al.
Published: (2024)

Explainable AI-Guided Efficient Approximate DNN Generation for Multi-Pod Systolic Arrays
by: Siddique, Ayesha, et al.
Published: (2025)

Robust Shielding for Safe Reinforcement Learning
by: Court, Edwin Hamel-De le, et al.
Published: (2026)

Decentralized Planning Using Probabilistic Hyperproperties
by: Pontiggia, Francesco, et al.
Published: (2025)

BURNS: Backward Underapproximate Reachability for Neural-Feedback-Loop Systems
by: Sidrane, Chelsea, et al.
Published: (2025)

Temporal Planning via Interval Logic Satisfiability for Autonomous Systems
by: Ramirez, Miquel, et al.
Published: (2024)

TTT: A Temporal Refinement Heuristic for Tenuously Tractable Discrete Time Reachability Problems
by: Sidrane, Chelsea, et al.
Published: (2024)

Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives
by: Belly, Marius, et al.
Published: (2024)

Thinking Out of the Box: Hybrid SAT Solving by Unconstrained Continuous Optimization
by: Zhang, Zhiwei, et al.
Published: (2025)

BoxLitE: A Faithful Knowledge Base Embedding Based on Convex Optimization
by: Lourenço, Bruno F., et al.
Published: (2026)

Inductive Generalization in Reinforcement Learning from Specifications
by: Subramanian, Vignesh, et al.
Published: (2024)

SMLP: Symbolic Machine Learning Prover
by: Brauße, Franz, et al.
Published: (2024)

Compositional Shielding and Reinforcement Learning for Multi-Agent Systems
by: Brorholt, Asger Horn, et al.
Published: (2024)

SMLP: Symbolic Machine Learning Prover (User Manual)
by: Brauße, Franz, et al.
Published: (2024)

FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning
by: Khalil, Khurram, et al.
Published: (2025)

Safe Reach Set Computation via Neural Barrier Certificates
by: Abate, Alessandro, et al.
Published: (2024)

Compositional Inductive Invariant Based Verification of Neural Network Controlled Systems
by: Zhou, Yuhao, et al.
Published: (2023)

A General Framework for Verification and Control of Dynamical Models via Certificate Synthesis
by: Edwards, Alec, et al.
Published: (2023)

Fossil 2.0: Formal Certificate Synthesis for the Verification and Control of Dynamical Models
by: Edwards, Alec, et al.
Published: (2023)

A Reinforcement Learning based Reset Policy for CDCL SAT Solvers
by: Li, Chunxiao, et al.
Published: (2024)