Cover Image

UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Oh, Sejoon, Jin, Yiqiao, Sharma, Megha, Kim, Donghyun, Ma, Eric, Verma, Gaurav, Kumar, Srijan
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adversarial Text Rewriting for Text-aware Recommender Systems
by: Oh, Sejoon, et al.
Published: (2024)

Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
by: Verma, Gaurav, et al.
Published: (2024)

MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms
by: Jin, Yiqiao, et al.
Published: (2024)

Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings
by: Sharma, Kartik, et al.
Published: (2025)

ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
by: Aswal, Darpan, et al.
Published: (2025)

FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning
by: Oh, Sejoon, et al.
Published: (2024)

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection
by: Giarrusso, Francesco, et al.
Published: (2025)

MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety
by: Yang, Yahan, et al.
Published: (2025)

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
by: Jin, Yiqiao, et al.
Published: (2026)

Characterizing, Detecting, and Predicting Online Ban Evasion
by: Niverthi, Manoj, et al.
Published: (2022)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
by: Zhao, Yunhan, et al.
Published: (2026)

PoseGuard: Pose-Guided Generation with Safety Guardrails
by: Wang, Kongxin, et al.
Published: (2025)

Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
by: Yin, Ziyi, et al.
Published: (2025)

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

Toward Butler's conjecture
by: Kim, Donghyun, et al.
Published: (2022)

Toward Butler's conjecture
by: Donghyun Kim, et al.
Published: (2026)

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks
by: Liu, Sheng, et al.
Published: (2025)

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
by: Sharma, Kartik, et al.
Published: (2025)

ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
by: Wang, Yan, et al.
Published: (2026)

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
by: Yu, Jiaqi, et al.
Published: (2026)

Towards Fair Graph Anomaly Detection: Problem, Benchmark Datasets, and Evaluation
by: Neo, Neng Kai Nigel, et al.
Published: (2024)

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

A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models
by: Verma, Gaurav, et al.
Published: (2025)

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

Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
by: Kang, Mintong, et al.
Published: (2025)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
by: Wang, Youze, et al.
Published: (2025)

A Survey on the Role of Crowds in Combating Online Misinformation: Annotators, Evaluators, and Creators
by: He, Bing, et al.
Published: (2023)

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

Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
by: Young, Richard J.
Published: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
by: Cui, Kaiyuan, et al.
Published: (2026)

MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models
by: Agarwal, Vibhor, et al.
Published: (2024)

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
by: Park, Yein, et al.
Published: (2025)

SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
by: Jin, Yiqiao, et al.
Published: (2025)

The Influence of Text Variation on User Engagement in Cross-Platform Content Sharing
by: Hu, Yibo, et al.
Published: (2025)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
by: Wang, Libo
Published: (2024)

A Thousand Words or An Image: Studying the Influence of Persona Modality in Multimodal LLMs
by: Broomfield, Julius, et al.
Published: (2025)

Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling
by: Byeon, Junhyeong, et al.
Published: (2026)

SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
by: Jin, Yiqiao, et al.
Published: (2025)

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
by: Teng, Ma, et al.
Published: (2024)