Copertina

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Nanxi, Zhao, Zhengyue, Xiao, Chaowei
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
di: Li, Nanxi, et al.
Pubblicazione: (2025)

SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability
di: Xu, Peiyang, et al.
Pubblicazione: (2025)

AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling
di: Liu, Xiaogeng, et al.
Pubblicazione: (2025)

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
di: Zafar, Osama, et al.
Pubblicazione: (2026)

No Free Lunch with Guardrails
di: Kumar, Divyanshu, et al.
Pubblicazione: (2025)

Provably Secure Agent Guardrail
di: Wu, Benlong, et al.
Pubblicazione: (2026)

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
di: Liu, Xiaogeng, et al.
Pubblicazione: (2026)

OET: Optimization-based prompt injection Evaluation Toolkit
di: Pan, Jinsheng, et al.
Pubblicazione: (2025)

RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
di: Wang, Peiran, et al.
Pubblicazione: (2024)

A Comparative Evaluation of AI Agent Security Guardrails
di: Li, Qi, et al.
Pubblicazione: (2026)

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
di: Wen, Ruoyao, et al.
Pubblicazione: (2026)

Enhancing Guardrails for Safe and Secure Healthcare AI
di: Gangavarapu, Ananya
Pubblicazione: (2024)

SoK: Evaluating Jailbreak Guardrails for Large Language Models
di: Wang, Xunguang, et al.
Pubblicazione: (2025)

ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
di: Zhao, Zhengyue, et al.
Pubblicazione: (2025)

Defenses Against Prompt Attacks Learn Surface Heuristics
di: Li, Shawn, et al.
Pubblicazione: (2026)

JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
di: Nian, Yi, et al.
Pubblicazione: (2025)

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
di: Luo, Weidi, et al.
Pubblicazione: (2025)

WIPI: A New Web Threat for LLM-Driven Web Agents
di: Wu, Fangzhou, et al.
Pubblicazione: (2024)

AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
di: Wang, Yu, et al.
Pubblicazione: (2024)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
di: Li, Hao, et al.
Pubblicazione: (2026)

Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7
di: Aydin, Yuksel
Pubblicazione: (2025)

Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders & Researchers
di: Bertollo, Giacomo, et al.
Pubblicazione: (2025)

Balancing Privacy and Efficiency: Music Information Retrieval via Additive Homomorphic Encryption
di: Wang, William Zerong, et al.
Pubblicazione: (2025)

LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance
di: Wang, Yu, et al.
Pubblicazione: (2025)

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
di: Li, Hao, et al.
Pubblicazione: (2025)

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks
di: Wu, ChenYu, et al.
Pubblicazione: (2025)

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
di: Wang, Xi, et al.
Pubblicazione: (2026)

A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
di: Wu, Fangzhou, et al.
Pubblicazione: (2024)

On Automating Security Policies with Contemporary LLMs
di: Saura, Pablo Fernández, et al.
Pubblicazione: (2025)

OneShield -- the Next Generation of LLM Guardrails
di: DeLuca, Chad, et al.
Pubblicazione: (2025)

How Good LLM-Generated Password Policies Are?
di: Vaidya, Vivek, et al.
Pubblicazione: (2025)

RAGent: Retrieval-based Access Control Policy Generation
di: Jayasundara, Sakuna Harinda, et al.
Pubblicazione: (2024)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
di: Xiang, Chong, et al.
Pubblicazione: (2026)

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
di: Li, Hao, et al.
Pubblicazione: (2024)

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
di: Simoni, Marco, et al.
Pubblicazione: (2025)

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
di: Jin, Xisen, et al.
Pubblicazione: (2026)

NeuroFilter: Privacy Guardrails for Conversational LLM Agents
di: Das, Saswat, et al.
Pubblicazione: (2026)

APEX: Agent Payment Execution with Policy for Autonomous Agent API Access
di: Uddin, Mohd Safwan, et al.
Pubblicazione: (2026)

AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
di: Zheng, Ye, et al.
Pubblicazione: (2025)

A BERT-based Empirical Study of Privacy Policies' Compliance with GDPR
di: Zhang, Lu, et al.
Pubblicazione: (2024)