Imagen de Portada

Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhi, Dapeng, Wang, Peixin, Liu, Si, Ong, Luke, Zhang, Min
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Quantitative Verification of Omega-regular Properties in Probabilistic Programming
por: Wang, Peixin, et al.
Publicado: (2025)

Quantitative Verification of Constrained Occupation Time for Stochastic Discrete-time Systems
por: Xue, Bai, et al.
Publicado: (2026)

Relational DNN Verification With Cross Executional Bound Refinement
por: Banerjee, Debangshu, et al.
Publicado: (2024)

Harnessing Neuron Stability to Improve DNN Verification
por: Duong, Hai, et al.
Publicado: (2024)

Conformal Prediction Meets Long-tail Classification
por: Liu, Shuqi, et al.
Publicado: (2025)

Quantitative Verification of Fairness in Tree Ensembles
por: Zhao, Zhenjiang, et al.
Publicado: (2025)

Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation
por: Sano, Teruki, et al.
Publicado: (2025)

Enlightenment Period Improving DNN Performance
por: Liu, Tiantian, et al.
Publicado: (2025)

Refined Barrier Conditions for Finite-Time Safety and Reach-Avoid Guarantees in Stochastic Systems
por: Xue, Bai, et al.
Publicado: (2025)

Efficient Verification of Neural Control Barrier Functions with Smooth Nonlinear Activations
por: Zhang, Jun, et al.
Publicado: (2026)

Information-Theoretic Limits of Safety Verification for Self-Improving Systems
por: Scrivens, Arsenios
Publicado: (2026)

FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs
por: Goh, Si Qi, et al.
Publicado: (2025)

When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer
por: Liu, Shuqi, et al.
Publicado: (2026)

Image Hijacks: Adversarial Images can Control Generative Models at Runtime
por: Bailey, Luke, et al.
Publicado: (2023)

Energy-Aware DNN Graph Optimization
por: Wang, Yu, et al.
Publicado: (2020)

Reinforcement Learning with $ω$-Regular Objectives and Constraints
por: Wagner, Dominik, et al.
Publicado: (2025)

Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support
por: Reichelt, Tim, et al.
Publicado: (2023)

SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints
por: Wagner, Dominik, et al.
Publicado: (2025)

Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification
por: Yu, Hang, et al.
Publicado: (2026)

Tighter Truncated Rectangular Prism Approximation for RNN Robustness Verification
por: Lin, Xingqi, et al.
Publicado: (2025)

Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
por: Flinkow, Thomas, et al.
Publicado: (2026)

Rethinking the Potential of Layer Freezing for Efficient DNN Training
por: Yang, Chence, et al.
Publicado: (2025)

MLTCP: Congestion Control for DNN Training
por: Rajasekaran, Sudarsanan, et al.
Publicado: (2024)

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
por: Li, Mingjie, et al.
Publicado: (2025)

Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization
por: Chen, Yuen, et al.
Publicado: (2025)

MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators
por: Leon, Vasileios, et al.
Publicado: (2025)

DNN Modularization via Activation-Driven Training
por: Ngo, Tuan, et al.
Publicado: (2024)

Runtime Stealthy Perception Attacks against DNN-based Adaptive Cruise Control Systems
por: Zhou, Xugui, et al.
Publicado: (2023)

Feather: An Elegant Solution to Effective DNN Sparsification
por: Georgoulakis, Athanasios Glentis, et al.
Publicado: (2023)

Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations
por: Marks, Luke
Publicado: (2023)

Quantitative Verification of Finite-Time Constrained Occupation Measures for Continuous-time Stochastic Systems
por: Xue, Bai, et al.
Publicado: (2026)

PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks
por: Li, Xuran, et al.
Publicado: (2025)

Empirical Validation of the Classification-Verification Dichotomy for AI Safety Gates
por: Scrivens, Arsenios
Publicado: (2026)

Pseudo-Formalization for Automatic Proof Verification
por: Barkallah, Slim, et al.
Publicado: (2026)

Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems
por: ElShehaby, Mohamed, et al.
Publicado: (2025)

Simultaneous Identification of Sparse Structures and Communities in Heterogeneous Graphical Models
por: Shi, Dapeng, et al.
Publicado: (2024)

Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)
por: Zhao, Taibiao, et al.
Publicado: (2026)

Maintaining and Managing Road Quality:Using MLP and DNN
por: Maotwana, Makgotso Jacqueline
Publicado: (2024)

Safe Multi-Agent Deep Reinforcement Learning for Privacy-Aware Edge-Device Collaborative DNN Inference
por: Wang, Hong, et al.
Publicado: (2026)

Hardware-Aware DNN Compression for Homogeneous Edge Devices
por: Zhang, Kunlong, et al.
Publicado: (2025)