Buchumschlag

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Hao, Ren, Yubing, Cao, Yanan, Li, Yingjie, Fang, Fang, Wang, Shi, Guo, Li
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
von: Li, Hao, et al.
Veröffentlicht: (2025)

From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
von: Wang, Yidan, et al.
Veröffentlicht: (2025)

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
von: Wang, Zhuoshang, et al.
Veröffentlicht: (2026)

WorldCup Sampling for Multi-bit LLM Watermarking
von: Wang, Yidan, et al.
Veröffentlicht: (2026)

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
von: Wang, Yidan, et al.
Veröffentlicht: (2025)

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
von: An, Li, et al.
Veröffentlicht: (2025)

Revisiting the Robustness of Watermarking to Paraphrasing Attacks
von: Rastogi, Saksham, et al.
Veröffentlicht: (2024)

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
von: Ren, Jie, et al.
Veröffentlicht: (2023)

DINA: A Dual Defense Framework Against Internal Noise and External Attacks in Natural Language Processing
von: Chuang, Ko-Wei, et al.
Veröffentlicht: (2025)

Privacy in Large Language Models: Attacks, Defenses and Future Directions
von: Li, Haoran, et al.
Veröffentlicht: (2023)

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

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
von: He, Yu, et al.
Veröffentlicht: (2025)

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
von: Guo, Zhen, et al.
Veröffentlicht: (2026)

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
von: Li, Yu, et al.
Veröffentlicht: (2026)

Duwak: Dual Watermarks in Large Language Models
von: Zhu, Chaoyi, et al.
Veröffentlicht: (2024)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
von: Yi, Biao, et al.
Veröffentlicht: (2025)

Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images
von: Xie, JinFeng, et al.
Veröffentlicht: (2026)

PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
von: Mangaokar, Neal, et al.
Veröffentlicht: (2024)

FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
von: Wang, Jiongxiao, et al.
Veröffentlicht: (2024)

Removal Attack and Defense on AI-generated Content Latent-based Watermarking
von: Lee, De Zhang, et al.
Veröffentlicht: (2025)

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
von: Li, Yuexin, et al.
Veröffentlicht: (2026)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
von: Yu, Miao, et al.
Veröffentlicht: (2024)

Yet Another Watermark for Large Language Models
von: Bao, Siyuan, et al.
Veröffentlicht: (2025)

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
von: Zhou, Tong, et al.
Veröffentlicht: (2024)

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game
von: Xie, Yuanbo, et al.
Veröffentlicht: (2026)

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
von: Wang, Zihan, et al.
Veröffentlicht: (2025)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
von: Zhao, Haodong, et al.
Veröffentlicht: (2024)

Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
von: Chowdhury, Arijit Ghosh, et al.
Veröffentlicht: (2024)

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
von: Wang, Zihan, et al.
Veröffentlicht: (2025)

SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
von: Afane, Mohamed, et al.
Veröffentlicht: (2025)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
von: Zeng, Yifan, et al.
Veröffentlicht: (2024)

Denial-of-Service Poisoning Attacks against Large Language Models
von: Gao, Kuofeng, et al.
Veröffentlicht: (2024)

Towards Code Watermarking with Dual-Channel Transformations
von: Yang, Borui, et al.
Veröffentlicht: (2023)

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
von: Zhao, Shuai, et al.
Veröffentlicht: (2024)

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

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
von: Shetty, Anudeex, et al.
Veröffentlicht: (2024)

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
von: Huo, Jiahao, et al.
Veröffentlicht: (2026)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
von: Chen, Taiye, et al.
Veröffentlicht: (2025)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
von: Zhang, Xiaozhe, et al.
Veröffentlicht: (2026)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
von: Zhang, Xu, et al.
Veröffentlicht: (2025)