Cover Image

GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Haibo, Chen, Ruoxi, Zhang, Peiyan, Zhou, Andy, Cheng, Zelei, Wang, Haohan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models
by: Jin, Haibo, et al.
Published: (2024)

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
by: Jin, Haibo, et al.
Published: (2025)

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
by: Jin, Haibo, et al.
Published: (2024)

JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
by: Jin, Haibo, et al.
Published: (2024)

Reasoning Can Hurt the Inductive Abilities of Large Language Models
by: Jin, Haibo, et al.
Published: (2025)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
by: Zhou, Andy, et al.
Published: (2024)

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
by: Zheng, Haohan, et al.
Published: (2025)

LLM-driven Medical Report Generation via Communication-efficient Heterogeneous Federated Learning
by: Che, Haoxuan, et al.
Published: (2025)

Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
by: Pantazopoulos, Georgios, et al.
Published: (2024)

NEURO-GUARD: Neuro-Symbolic Generalization and Unbiased Adaptive Routing for Diagnostics -- Explainable Medical AI
by: Urooj, Midhat, et al.
Published: (2025)

EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
by: Chen, Ruoxi, et al.
Published: (2023)

Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents
by: Zhang, Xueqiao, et al.
Published: (2025)

PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation
by: Jin, Haibo, et al.
Published: (2023)

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
by: Li, Yifan, et al.
Published: (2024)

Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis
by: Yeh, Chun-Hsiao, et al.
Published: (2024)

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
by: Zhou, Andy, et al.
Published: (2023)

Adaptive Vision-Language Model Routing for Computer Use Agents
by: Liu, Xunzhuo, et al.
Published: (2026)

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
by: Zhang, Peiyan, et al.
Published: (2025)

Context Cascade Compression: Exploring the Upper Limits of Text Compression
by: Liu, Fanfan, et al.
Published: (2025)

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
by: Jiang, Lei, et al.
Published: (2025)

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
by: Liu, Xuannan, et al.
Published: (2024)

Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge
by: Wang, Haibo, et al.
Published: (2024)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
by: Jin, Haibo, et al.
Published: (2021)

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
by: Leng, Jixuan, et al.
Published: (2025)

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders
by: Zhang, Yuqi, et al.
Published: (2025)

LLMs can Compress LLMs: Adaptive Pruning by Agents
by: Kodathala, Sai Varun, et al.
Published: (2026)

GUIDE: A Guideline-Guided Dataset for Instructional Video Comprehension
by: Liang, Jiafeng, et al.
Published: (2024)

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
by: Ma, Chuang, et al.
Published: (2026)

Multimodal Event Detection: Current Approaches and Defining the New Playground through LLMs and VLMs
by: Dey, Abhishek, et al.
Published: (2025)

Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction
by: Teng, Matthew Kit Khinn, et al.
Published: (2025)

ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
by: Yang, Guan-Yan, et al.
Published: (2025)

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
by: Han, Peitao, et al.
Published: (2026)

Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry
by: Hou, Wenjun, et al.
Published: (2024)

Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
by: Chen, Dongping, et al.
Published: (2024)

Jailbreaking Attack against Multimodal Large Language Model
by: Niu, Zhenxing, et al.
Published: (2024)

Design as Desired: Utilizing Visual Question Answering for Multimodal Pre-training
by: Su, Tongkun, et al.
Published: (2024)

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
by: Guan, Tianrui, et al.
Published: (2023)

EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents
by: Cheng, Zhili, et al.
Published: (2025)

Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs
by: Zheng, Huan, et al.
Published: (2026)

ColorBlindnessEval: Can Vision-Language Models Pass Color Blindness Tests?
by: Ling, Zijian, et al.
Published: (2025)