Cover Image

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hung, Ki Sen, Yang, Xi, Liu, Chang, Li, Haoran, Chen, Kejiang, Fan, Changxuan, Kwok, Tsun On, Zhang, Weiming, Li, Xiaomeng, Song, Yangqiu
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security cs.CR
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Specification to Deployment: Empirical Evidence from a W3C VC + DID Trust Infrastructure for Autonomous Agents
by: Kroehl, Lars Kersten
Published: (2026)

Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates
by: Shang, Zhenhang, et al.
Published: (2026)

Security Friction Quotient for Zero Trust Identity Policy with Empirical Validation
by: Youssef, Michel
Published: (2025)

FSPQ-4096: Fast Scalable Pre-Quantum Virtual Register Architecture for Cryptographic Entropy Generation
by: Pirolo, Andrés Sebastián, et al.
Published: (2026)

HADA: Human-AI Agent Decision Alignment Architecture
by: Pitkäranta, Tapio, et al.
Published: (2025)

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
by: Zhao, Haotian, et al.
Published: (2026)

Practical Code RAG at Scale: Task-Aware Retrieval Design Choices under Compute Budgets
by: Galimzyanov, Timur, et al.
Published: (2025)

Semantic Web and Software Agents -- A Forgotten Wave of Artificial Intelligence?
by: Pitkäranta, Tapio, et al.
Published: (2025)

Where did you get that? Towards Summarization Attribution for Analysts
by: B, Violet, et al.
Published: (2025)

FactoryBench: Evaluating Industrial Machine Understanding
by: Merzouki, Yanis, et al.
Published: (2026)

CapTune: Adapting Non-Speech Captions With Anchored Generative Models
by: Huang, Jeremy Zhengqi, et al.
Published: (2025)

Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models
by: Leyva-Vázquez, Maikel Yelandi, et al.
Published: (2026)

Optimal Transport-Guided Safety in Temporal Difference Reinforcement Learning
by: Shahrooei, Zahra, et al.
Published: (2025)

Accelerating Monte-Carlo Tree Search with Optimized Posterior Policies
by: Frankston, Keith, et al.
Published: (2026)

WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games
by: Zhang, Wenyu, et al.
Published: (2026)

PG-Triggers: Triggers for Property Graphs
by: Ceri, Stefano, et al.
Published: (2023)

Can AI Outperform Human Experts in Creating Social Media Creatives?
by: Park, Eunkyung, et al.
Published: (2024)

LLMs: A Game-Changer for Software Engineers?
by: Haque, Md Asraful
Published: (2024)

GraphCompNet: A Position-Aware Model for Predicting and Compensating Shape Deviations in 3D Printing
by: Lee, Juheon, et al.
Published: (2025)

Self-Improving Multilingual Long Reasoning via Translation-Reasoning Integrated Training
by: Liu, Junxiao, et al.
Published: (2026)

HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection
by: Wang, Han, et al.
Published: (2025)

Over-Squashing in Graph Neural Networks: A Comprehensive survey
by: Akansha, Singh
Published: (2023)

The NordDRG AI Benchmark for Large Language Models
by: Pitkäranta, Tapio
Published: (2025)

Addressing Sustainability-IN Software Challenges
by: Calero, Coral, et al.
Published: (2024)

CENTS: Generating synthetic electricity consumption time series for rare and unseen scenarios
by: Fuest, Michael, et al.
Published: (2025)

LLMTrace: A Corpus for Classification and Fine-Grained Localization of AI-Written Text
by: Tolstykh, Irina, et al.
Published: (2025)

Relation Extraction Capabilities of LLMs on Clinical Text: A Bilingual Evaluation for English and Turkish
by: Aidynkyzy, Aidana, et al.
Published: (2026)

TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya
by: Teklehaymanot, Hailay, et al.
Published: (2024)

Optimizing Ride-Pooling Revenue: Pricing Strategies and Driver-Traveller Dynamics
by: Akhtar, Usman, et al.
Published: (2024)

Autonomous motion in changing environment, fibrations and reaction mechanisms
by: Farber, Michael, et al.
Published: (2025)

Optimizing Hospital Capacity During Pandemics: A Dual-Component Framework for Strategic Patient Relocation
by: Tabatabaee, Sadaf, et al.
Published: (2026)

MPLS y ATM como tecnologías backbone para la transferencia de videoconferencia
by: DANILO LÓPEZ
Published: (2012)

RA: A machine based rational agent, Part 2, Preliminary test
by: Pantelis, G.
Published: (2024)

Conditional Shift-Robust Conformal Prediction for Graph Neural Network
by: Akansha, S.
Published: (2024)

RA: A machine based rational agent, Part 1
by: Pantelis, G.
Published: (2024)

Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks
by: Wu, Jingcheng, et al.
Published: (2026)

KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving
by: Zhong, Zhiqing, et al.
Published: (2026)

Towards Objective Gastrointestinal Auscultation: Automated Segmentation and Annotation of Bowel Sound Patterns
by: Mansour, Zahra, et al.
Published: (2026)

Benchmarking machine learning for bowel sound pattern classification from tabular features to pretrained models
by: Mansour, Zahra, et al.
Published: (2025)

From Questions to Insights: Exploring XAI Challenges Reported on Stack Overflow Questions
by: Roy, Saumendu, et al.
Published: (2025)