Cover Image

$B^4$: A Black-Box Scrubbing Attack on LLM Watermarks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Baizhou, Pu, Xiao, Wan, Xiaojun
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
by: Shen, Huanming, et al.
Published: (2025)

WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
by: Huang, Baizhou, et al.
Published: (2024)

QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs
by: Zhu, Junlin, et al.
Published: (2026)

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles
by: Pu, Xiao, et al.
Published: (2024)

Cross-Lingual Summarization as a Black-Box Watermark Removal Attack
by: Ganesan, Gokul
Published: (2025)

Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
by: Huang, Baizhou, et al.
Published: (2023)

LLM-based NLG Evaluation: Current Status and Challenges
by: Gao, Mingqi, et al.
Published: (2024)

A Watermark for Black-Box Language Models
by: Bahri, Dara, et al.
Published: (2024)

MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency
by: Zhang, Junzhe, et al.
Published: (2024)

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

Enhancing Jailbreak Attacks with Diversity Guidance
by: Zhang, Xu, et al.
Published: (2024)

Black-Box Guardrail Reverse-engineering Attack
by: Yao, Hongwei, et al.
Published: (2025)

Knowledge Distillation of Black-Box Large Language Models
by: Chen, Hongzhan, et al.
Published: (2024)

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
by: Chen, Bocheng, et al.
Published: (2024)

BinarySelect to Improve Accessibility of Black-Box Attack Research
by: Ghosh, Shatarupa, et al.
Published: (2024)

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty
by: Feng, Yu, et al.
Published: (2024)

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference
by: Zhang, Libo, et al.
Published: (2024)

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

Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling
by: Ruan, Jie, et al.
Published: (2024)

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
by: Liu, Han, et al.
Published: (2024)

Bounded Behavioral Indistinguishability for Black-Box LLM Distillation
by: Hasan, Munawar
Published: (2026)

Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA
by: Zhang, Yiran, et al.
Published: (2025)

Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks
by: An, Haonan, et al.
Published: (2024)

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
by: Akbar-Tajari, Mohammad, et al.
Published: (2025)

All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
by: Takemoto, Kazuhiro
Published: (2024)

Towards Universal and Black-Box Query-Response Only Attack on LLMs with QROA
by: Jawad, Hussein, et al.
Published: (2024)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
by: Mehrotra, Anay, et al.
Published: (2023)

A Transfer Attack to Image Watermarks
by: Hu, Yuepeng, et al.
Published: (2024)

Selecting Large Language Model to Fine-tune via Rectified Scaling Law
by: Lin, Haowei, et al.
Published: (2024)

Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators
by: Chang, Jiayi, et al.
Published: (2025)

Kov: Transferable and Naturalistic Black-Box LLM Attacks using Markov Decision Processes and Tree Search
by: Moss, Robert J.
Published: (2024)

Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
by: Gohil, Vasudev
Published: (2025)

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
by: Cheng, Jiale, et al.
Published: (2023)

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
by: Zhang, Yuanhe, et al.
Published: (2024)

SwissNYF: Tool Grounded LLM Agents for Black Box Setting
by: Kumar, Somnath Sendhil, et al.
Published: (2024)

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods
by: Doshi, Jai, et al.
Published: (2024)

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
by: Liang, Jiacheng, et al.
Published: (2024)

Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow
by: Zhou, Ziyu, et al.
Published: (2025)

Watermarking LLM Agent Trajectories
by: Meng, Wenlong, et al.
Published: (2026)

HYDRA: Model Factorization Framework for Black-Box LLM Personalization
by: Zhuang, Yuchen, et al.
Published: (2024)