Copertina

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lv, Peizhuo, Li, Pan, Zhu, Shenchen, Zhang, Shengzhi, Chen, Kai, Liang, Ruigang, Yue, Chang, Xiang, Fan, Cai, Yuling, Ma, Hualong, Zhang, Yingjun, Meng, Guozhu
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MEA-Defender: A Robust Watermark against Model Extraction Attack
di: Lv, Peizhuo, et al.
Pubblicazione: (2024)

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
di: Lv, Peizhuo, et al.
Pubblicazione: (2025)

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
di: Lv, Peizhuo, et al.
Pubblicazione: (2025)

A Model Stealing Attack Against Multi-Exit Networks
di: Pan, Li, et al.
Pubblicazione: (2023)

ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
di: Jiang, Yongqi, et al.
Pubblicazione: (2026)

Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
di: Zhao, Xiangyu, et al.
Pubblicazione: (2024)

Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders
di: Xin, Yuan, et al.
Pubblicazione: (2024)

AuthNet: Neural Network with Integrated Authentication Logic
di: Cai, Yuling, et al.
Pubblicazione: (2024)

CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer
di: Zhao, Yue, et al.
Pubblicazione: (2026)

SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
di: Wang, Mingsi, et al.
Pubblicazione: (2025)

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
di: Zhou, Gaoyue, et al.
Pubblicazione: (2024)

Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models
di: Lv, Song-Lin, et al.
Pubblicazione: (2025)

Turn-Based Structural Triggers: Prompt-Free Backdoors in Multi-Turn LLMs
di: Lu, Yiyang, et al.
Pubblicazione: (2026)

TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity
di: Chen, Yuzhuo, et al.
Pubblicazione: (2025)

Localizing Memorization in SSL Vision Encoders
di: Wang, Wenhao, et al.
Pubblicazione: (2024)

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
di: Zhang, Zhicheng, et al.
Pubblicazione: (2025)

Hidden in Plain Sight: Exploring Chat History Tampering in Interactive Language Models
di: Wei, Cheng'an, et al.
Pubblicazione: (2024)

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

Black-Box Detection of Language Model Watermarks
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2024)

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

TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers
di: Xu, Hengyuan, et al.
Pubblicazione: (2024)

SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
di: Zhang, Xin, et al.
Pubblicazione: (2026)

PuzzleMark: Implicit Jigsaw Learning for Robust Code Dataset Watermarking in Neural Code Completion Models
di: Huang, Haocheng, et al.
Pubblicazione: (2026)

Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
di: Pan, Minzhou, et al.
Pubblicazione: (2024)

On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation
di: Wu, Di, et al.
Pubblicazione: (2024)

Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
di: Han, Tingxu, et al.
Pubblicazione: (2024)

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
di: Zhou, Ziqi, et al.
Pubblicazione: (2024)

Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Study
di: An, Keyu, et al.
Pubblicazione: (2024)

A Robust Zero‐Watermarking Algorithm for Spatiotemporal Trajectory Data Protection
di: Jianing Xie, et al.
Pubblicazione: (2025)

Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection
di: Zhang, Yinghe, et al.
Pubblicazione: (2025)

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
di: Müller, Andreas, et al.
Pubblicazione: (2024)

JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
di: Pan, Minzhou, et al.
Pubblicazione: (2024)

Online Federation For Mixtures of Proprietary Agents with Black-Box Encoders
di: Yang, Xuwei, et al.
Pubblicazione: (2025)

WeakSupCon: Weakly Supervised Contrastive Learning for Encoder Pre-training
di: Zhang, Bodong, et al.
Pubblicazione: (2025)

Reconsidering Degeneration of Token Embeddings with Definitions for Encoder-based Pre-trained Language Models
di: Zhang, Ying, et al.
Pubblicazione: (2024)

Multimodal Autoregressive Pre-training of Large Vision Encoders
di: Fini, Enrico, et al.
Pubblicazione: (2024)

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

$B^4$: A Black-Box Scrubbing Attack on LLM Watermarks
di: Huang, Baizhou, et al.
Pubblicazione: (2024)

Pre-trained Prompt-driven Semi-supervised Local Community Detection
di: Ni, Li, et al.
Pubblicazione: (2025)

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
di: Zhao, Qitao, et al.
Pubblicazione: (2025)