Cover Image

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mu, Junjie, Ying, Zonghao, Fan, Zhekui, Jing, Zonglei, Zhang, Yaoyuan, Yu, Zhengmin, Zhang, Wenxin, Zou, Quanchen, Zhang, Xiangzheng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
by: Zou, Quanchen, et al.
Published: (2026)

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
by: Ying, Zonghao, et al.
Published: (2024)

TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
by: Du, Mengyao, et al.
Published: (2026)

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

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

WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes
by: Valbuena, Victor
Published: (2024)

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
by: Basani, Advik Raj, et al.
Published: (2024)

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

The Resurgence of GCG Adversarial Attacks on Large Language Models
by: Tan, Yuting, et al.
Published: (2025)

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
by: Wang, Haowei, et al.
Published: (2025)

Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models
by: Eddoubi, Hicham, et al.
Published: (2026)

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
by: Li, Xiao, et al.
Published: (2024)

Universal Jailbreak Suffixes Are Strong Attention Hijackers
by: Ben-Tov, Matan, et al.
Published: (2025)

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

GCG Attack On A Diffusion LLM
by: Neyroud, Ruben, et al.
Published: (2025)

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
by: Wang, Shenao, et al.
Published: (2026)

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

Evolving Deception: When Agents Evolve, Deception Wins
by: Ying, Zonghao, et al.
Published: (2026)

TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
by: Wang, Yanting, et al.
Published: (2025)

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

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
by: Ma, Jiachen, et al.
Published: (2024)

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

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

Rethinking PGD Attack: Is Sign Function Necessary?
by: Yang, Junjie, et al.
Published: (2023)

Selective Masking Adversarial Attack on Automatic Speech Recognition Systems
by: Fang, Zheng, et al.
Published: (2025)

Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection
by: Zhou, Yuqi, et al.
Published: (2024)

Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
by: Li, Xiang, et al.
Published: (2025)

CS-Eval: A Comprehensive Large Language Model Benchmark for CyberSecurity
by: Yu, Zhengmin, et al.
Published: (2024)

Adversarial Suffix Filtering: a Defense Pipeline for LLMs
by: Khachaturov, David, et al.
Published: (2025)

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
by: Li, Yanzeng, et al.
Published: (2025)

Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache
by: Wang, Xinhai, et al.
Published: (2026)