Copertina

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zou, Quanchen, Li, Nizhang, Zhang, Wenxin, Lin, Jiaye, Zeng, Yangchen, Zhang, Xiangzheng, Ying, Zonghao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
di: Mu, Junjie, et al.
Pubblicazione: (2025)

SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
di: Ying, Zonghao, et al.
Pubblicazione: (2025)

Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking
di: Chen, Moyang, et al.
Pubblicazione: (2026)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
di: Liu, Zhe, et al.
Pubblicazione: (2026)

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs
di: Xu, Wenzhuo, et al.
Pubblicazione: (2026)

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
di: Ying, Zonghao, et al.
Pubblicazione: (2025)

Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application
di: Xu, Wenzhuo, et al.
Pubblicazione: (2025)

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
di: Ying, Zonghao, et al.
Pubblicazione: (2026)

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
di: Zou, Quanchen, et al.
Pubblicazione: (2026)

PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
di: Zou, Quanchen, et al.
Pubblicazione: (2025)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
di: Ying, Zonghao, et al.
Pubblicazione: (2026)

Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
di: Ying, Zonghao, et al.
Pubblicazione: (2025)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
di: Zhao, Yinzhi, et al.
Pubblicazione: (2026)

Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
di: Ying, Zonghao, et al.
Pubblicazione: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
di: Liu, Fan, et al.
Pubblicazione: (2024)

DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection
di: Zhou, Weilin, et al.
Pubblicazione: (2026)

Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles
di: Sun, Xiongtao, et al.
Pubblicazione: (2024)

Robust Privacy: Inference-Time Privacy through Certified Robustness
di: Jin, Jiankai, et al.
Pubblicazione: (2026)

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
di: Gao, Lang, et al.
Pubblicazione: (2024)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
di: Zhang, Zhexin, et al.
Pubblicazione: (2023)

Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling
di: Zhang, Deyue, et al.
Pubblicazione: (2025)

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
di: Zhao, Wei, et al.
Pubblicazione: (2024)

Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection
di: Zhou, Weilin, et al.
Pubblicazione: (2025)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
di: Robey, Alexander, et al.
Pubblicazione: (2023)

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

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
di: Xu, Zhangchen, et al.
Pubblicazione: (2024)

Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters
di: Mustafa, Ahmed B, et al.
Pubblicazione: (2026)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
di: Zhang, Zhexin, et al.
Pubblicazione: (2024)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
di: Zhao, Jiawei, et al.
Pubblicazione: (2024)

DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification
di: Li, Yu, et al.
Pubblicazione: (2025)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
di: Qian, Cheng, et al.
Pubblicazione: (2024)

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
di: Chew, Oscar, et al.
Pubblicazione: (2024)

Defending LLMs against Jailbreaking Attacks via Backtranslation
di: Wang, Yihan, et al.
Pubblicazione: (2024)

TrajLoom: Dense Future Trajectory Generation from Video
di: Zhang, Zewei, et al.
Pubblicazione: (2026)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
di: Chu, Junjie, et al.
Pubblicazione: (2024)

FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
di: Zhang, Zhiyuan, et al.
Pubblicazione: (2025)

TrajTok: Learning Trajectory Tokens enables better Video Understanding
di: Zheng, Chenhao, et al.
Pubblicazione: (2026)

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense
di: Liu, Cheng, et al.
Pubblicazione: (2026)

GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks
di: Li, Rongchang, et al.
Pubblicazione: (2024)

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
di: Ying, Zonghao, et al.
Pubblicazione: (2025)