Imagen de Portada

Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Songze, Cheng, Jiameng, Li, Yiming, Jia, Xiaojun, Tao, Dacheng
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
por: Li, Songze, et al.
Publicado: (2026)

TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
por: Li, Songze, et al.
Publicado: (2024)

SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
por: Yang, Wenyuan, et al.
Publicado: (2025)

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
por: Nguyen, Quang Duc, et al.
Publicado: (2026)

Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts
por: Wu, Yuanwei, et al.
Publicado: (2023)

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
por: Lin, Shuyi, et al.
Publicado: (2025)

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
por: Hossain, Ismail, et al.
Publicado: (2026)

MPC-Minimized Secure LLM Inference
por: Rathee, Deevashwer, et al.
Publicado: (2024)

Learning to Watermark LLM-generated Text via Reinforcement Learning
por: Xu, Xiaojun, et al.
Publicado: (2024)

Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
por: Wang, Zi, et al.
Publicado: (2024)

DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
por: Shao, Shuo, et al.
Publicado: (2025)

Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
por: Dong, Yingkai, et al.
Publicado: (2024)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
por: Nikolić, Kristina, et al.
Publicado: (2025)

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

A Causal Perspective for Enhancing Jailbreak Attack and Defense
por: Pan, Licheng, et al.
Publicado: (2026)

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
por: Ren, Zhiyao, et al.
Publicado: (2025)

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
por: Chen, Wenyu, et al.
Publicado: (2026)

Improved Large Language Model Jailbreak Detection via Pretrained Embeddings
por: Galinkin, Erick, et al.
Publicado: (2024)

Mitigating Many-Shot Jailbreaking
por: Ackerman, Christopher M., et al.
Publicado: (2025)

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
por: Liu, Xiaogeng, et al.
Publicado: (2024)

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
por: Yang, Junxiao, et al.
Publicado: (2025)

AdvPrefix: An Objective for Nuanced LLM Jailbreaks
por: Zhu, Sicheng, et al.
Publicado: (2024)

CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
por: Li, Yiming, et al.
Publicado: (2025)

LLM Jailbreak Detection for (Almost) Free!
por: Chen, Guorui, et al.
Publicado: (2025)

OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions
por: Huang, Yu-Shin, et al.
Publicado: (2024)

The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation
por: Jia, Hengrui, et al.
Publicado: (2025)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
por: Ghosal, Soumya Suvra, et al.
Publicado: (2024)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
por: Chen, Zhuowei, et al.
Publicado: (2025)

Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
por: Peng, Benji, et al.
Publicado: (2024)

Jailbreaking LLMs via Calibration
por: Lu, Yuxuan, et al.
Publicado: (2026)

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
por: Li, Jing-Jing, et al.
Publicado: (2025)

CertDW: Towards Certified Dataset Ownership Verification via Conformal Prediction
por: Qiao, Ting, et al.
Publicado: (2025)

AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
por: Chen, Guangke, et al.
Publicado: (2025)

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data
por: Zhou, Andy, et al.
Publicado: (2024)

MOVE: Effective and Harmless Ownership Verification via Embedded External Features
por: Li, Yiming, et al.
Publicado: (2022)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
por: Andriushchenko, Maksym, et al.
Publicado: (2024)

Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks
por: Nurlanov, Zhakshylyk, et al.
Publicado: (2026)

FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
por: Shao, Shuo, et al.
Publicado: (2025)

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
por: Shao, Shuo, et al.
Publicado: (2024)

OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
por: Wang, Kaixiang, et al.
Publicado: (2026)