Cover Image

DriveSafe: A Hierarchical Risk Taxonomy for Safety-Critical LLM-Based Driving Assistants

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumar, Abhishek, Tapwal, Riya, Maple, Carsten
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines
by: Tapwal, Riya, et al.
Published: (2026)

Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success
by: Maple, Carsten, et al.
Published: (2026)

Field-Localized Forgery Detection for Digital Identity Documents
by: Kumar, Abhishek, et al.
Published: (2026)

DriveSafe: A Framework for Risk Detection and Safety Suggestions in Driving Scenarios
by: Artham, Sainithin, et al.
Published: (2026)

Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges
by: Tapwal, Riya, et al.
Published: (2026)

CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems
by: Wang, Yannan, et al.
Published: (2026)

Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric Taxonomy
by: Stappen, Lukas, et al.
Published: (2026)

LLM-based Realistic Safety-Critical Driving Video Generation
by: Fu, Yongjie, et al.
Published: (2025)

Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous Driving
by: Li, Jingzheng, et al.
Published: (2025)

DriveSafer: End-to-End Autonomous Driving with Safety Guidance
by: Sural, Shounak, et al.
Published: (2026)

Hi-Drive: Hierarchical POMDP Planning for Safe Autonomous Driving in Diverse Urban Environments
by: Jin, Xuanjin, et al.
Published: (2024)

Dataset Safety in Autonomous Driving: Requirements, Risks, and Assurance
by: Abbaspour, Alireza, et al.
Published: (2025)

AnchorDrive: LLM Scenario Rollout with Anchor-Guided Diffusion Regeneration for Safety-Critical Scenario Generation
by: Jiang, Zhulin, et al.
Published: (2026)

Fusing Driver Perceived and Physical Risk for Safety Critical Scenario Screening in Autonomous Driving
by: Xiong, Chen, et al.
Published: (2026)

A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model
by: Yang, Shuo, et al.
Published: (2024)

Cross-Stage Coherence in Hierarchical Driving VQA: Explicit Baselines and Learned Gated Context Projectors
by: Jain, Gautam Kumar, et al.
Published: (2026)

Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
by: Bisconti, Piercosma, et al.
Published: (2025)

SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation
by: Ye, Hao, et al.
Published: (2025)

Hand by Hand: LLM Driving EMS Assistant for Operational Skill Learning
by: Xiang, Wei, et al.
Published: (2025)

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios
by: Gao, Yuan, et al.
Published: (2025)

LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarios
by: Peng, Mingxing, et al.
Published: (2025)

SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents
by: Chen, Ruolin, et al.
Published: (2025)

Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priors
by: Hao, Kunkun, et al.
Published: (2024)

VLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events
by: Bhat, Mohammad Qazim, et al.
Published: (2026)

Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories
by: Zhang, Zihan, et al.
Published: (2026)

CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models
by: Sheng, Zihao, et al.
Published: (2025)

Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF
by: Sun, Yuan, et al.
Published: (2024)

On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software
by: Nouri, Ali, et al.
Published: (2025)

Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories
by: Mirkhani, Hamidreza, et al.
Published: (2024)

Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving
by: Abouelazm, Ahmed, et al.
Published: (2025)

Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
by: Wei, Qi, et al.
Published: (2026)

LLM4Drive: A Survey of Large Language Models for Autonomous Driving
by: Yang, Zhenjie, et al.
Published: (2023)

SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving
by: Gao, Xiangbo, et al.
Published: (2025)

Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits
by: Hu, Yuting, et al.
Published: (2025)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
by: Liu, Zhe, et al.
Published: (2026)

Learning to Drive Safely with Hybrid Options
by: De Cooman, Bram, et al.
Published: (2025)

Agentic AI for Self-Driving Laboratories in Soft Matter: Taxonomy, Benchmarks,and Open Challenges
by: Chen, Xuanzhou, et al.
Published: (2026)

Auto-Evaluation: A Critical Measure in Driving Improvements in Quality and Safety of AI-Generated Lesson Resources
by: Clark, Hannah-Beth, et al.
Published: (2025)

DeepMF: Deep Motion Factorization for Closed-Loop Safety-Critical Driving Scenario Simulation
by: Li, Yizhe, et al.
Published: (2024)

Is Your VLM for Autonomous Driving Safety-Ready? A Comprehensive Benchmark for Evaluating External and In-Cabin Risks
by: Meng, Xianhui, et al.
Published: (2025)