Imagen de Portada

ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang, Yongqi, Gao, Yansong, Kuang, Boyu, Zhou, Chunyi, Fu, Anmin, Chen, Liquan
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
por: Lv, Peizhuo, et al.
Publicado: (2022)

Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
por: Dai, Zhiyang, et al.
Publicado: (2026)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
por: Li, Na, et al.
Publicado: (2025)

Intellectual Property Protection for Deep Learning Model and Dataset Intelligence
por: Jiang, Yongqi, et al.
Publicado: (2024)

Empowering IoT Firmware Secure Update with Customization Rights
por: Chen, Weihao, et al.
Publicado: (2025)

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

Decaf: Data Distribution Decompose Attack against Federated Learning
por: Dai, Zhiyang, et al.
Publicado: (2024)

TruVRF: Towards Triple-Granularity Verification on Machine Unlearning
por: Zhou, Chunyi, et al.
Publicado: (2024)

ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples
por: Yang, Yunfei, et al.
Publicado: (2025)

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
por: Li, Na, et al.
Publicado: (2024)

PhishSSL: Self-Supervised Contrastive Learning for Phishing Website Detection
por: Li, Wenhao, et al.
Publicado: (2025)

From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints
por: Gao, Yansong, et al.
Publicado: (2025)

Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
por: Fu, Anmin, et al.
Publicado: (2025)

Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services
por: Fu, Shaopeng, et al.
Publicado: (2024)

DeepiSign-G: Generic Watermark to Stamp Hidden DNN Parameters for Self-contained Tracking
por: Abuadbba, Alsharif, et al.
Publicado: (2024)

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

VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
por: Kong, Cong, et al.
Publicado: (2026)

Towards Traitor Tracing in Black-and-White-Box DNN Watermarking with Tardos-based Codes
por: Rodriguez-Lois, Elena, et al.
Publicado: (2023)

Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing
por: Ding, Ruyi, et al.
Publicado: (2024)

SLIM: Stealthy Low-Coverage Black-Box Watermarking via Latent-Space Confusion Zones
por: Wu, Hengyu, et al.
Publicado: (2026)

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

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

Why Neural Structural Obfuscation Can't Kill White-Box Watermarks for Good!
por: Jiang, Yanna, et al.
Publicado: (2026)

DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders
por: Hou, Sizai, et al.
Publicado: (2024)

Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
por: Wang, Nan, et al.
Publicado: (2025)

SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
por: Zheng, Mengxin, et al.
Publicado: (2023)

Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks
por: Fu, Wenkai, et al.
Publicado: (2025)

NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
por: Nguyen, David D., et al.
Publicado: (2026)

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

SEW: Strengthening Robustness of Black-box DNN Watermarking via Specificity Enhancement
por: Qiu, Huming, et al.
Publicado: (2026)

Enhancing Adversarial Transferability with Adversarial Weight Tuning
por: Chen, Jiahao, et al.
Publicado: (2024)

ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models
por: Qian, Yuqi, et al.
Publicado: (2026)

A Semi Black-Box Adversarial Bit-Flip Attack with Limited DNN Model Information
por: Ghavami, Behnam, et al.
Publicado: (2024)

SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection
por: Wang, Qiannan, et al.
Publicado: (2023)

Fading the Digital Ink: A Universal Black-Box Attack Framework for 3DGS Watermarking Systems
por: Zeng, Qingyuan, et al.
Publicado: (2025)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
por: Domico, Kyle, et al.
Publicado: (2025)

Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses Under White-Box and Black-Box Threats
por: Li, Adrian Shuai, et al.
Publicado: (2026)

Let Watermarks Speak: A Robust and Unforgeable Watermark for Language Models
por: Bai, Minhao
Publicado: (2024)

Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
por: Fu, Jiyuan, et al.
Publicado: (2024)

Performance-lossless Black-box Model Watermarking
por: Zhao, Na, et al.
Publicado: (2023)