Imagen de Portada

StealthMark: Harmless and Stealthy Ownership Verification for Medical Segmentation via Uncertainty-Guided Backdoors

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Qinkai, Zhang, Chong, Jin, Gaojie, Huang, Tianjin, Zhou, Wei, Li, Wenhui, Jin, Xiaobo, Huang, Bo, Zhao, Yitian, Yang, Guang, Lip, Gregory Y. H., Zheng, Yalin, Villavicencio, Aline, Meng, Yanda
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HoneyImage: Verifiable, Harmless, and Stealthy Dataset Ownership Verification for Image Models
por: Zhu, Zhihao, et al.
Publicado: (2025)

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers
por: Jin, Gaojie, et al.
Publicado: (2025)

Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
por: Jin, Gaojie, et al.
Publicado: (2026)

Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification
por: Li, Zhiying, et al.
Publicado: (2024)

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
por: Li, Xinyu, et al.
Publicado: (2025)

MOVE: Effective and Harmless Ownership Verification via Embedded External Features
por: Li, Yiming, et al.
Publicado: (2022)

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
por: Kong, Jiawei, et al.
Publicado: (2025)

Enhancing Robust Fairness via Confusional Spectral Regularization
por: Jin, Gaojie, et al.
Publicado: (2025)

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
por: Li, Xinyu, et al.
Publicado: (2026)

Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning
por: Bouaziz, Wassim, et al.
Publicado: (2024)

GLCP: Global-to-Local Connectivity Preservation for Tubular Structure Segmentation
por: Zhou, Feixiang, et al.
Publicado: (2025)

X-Mark: Saliency-Guided Robust Dataset Ownership Verification for Medical Imaging
por: Kulkarni, Pranav, et al.
Publicado: (2026)

CLIP-DR: Textual Knowledge-Guided Diabetic Retinopathy Grading with Ranking-aware Prompting
por: Yu, Qinkai, et al.
Publicado: (2024)

Goal-guided Generative Prompt Injection Attack on Large Language Models
por: Zhang, Chong, et al.
Publicado: (2024)

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
por: Hsu, Chia-Yi, et al.
Publicado: (2026)

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
por: Huang, Tianjin, et al.
Publicado: (2025)

Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning
por: Zhang, Chong, et al.
Publicado: (2023)

Shapley Uncertainty in Natural Language Generation
por: Zhu, Meilin, et al.
Publicado: (2025)

Parameterized Diffusion Optimization enabled Autoregressive Ordinal Regression for Diabetic Retinopathy Grading
por: Yu, Qinkai, et al.
Publicado: (2025)

Robust Incomplete-Modality Alignment for Ophthalmic Disease Grading and Diagnosis via Labeled Optimal Transport
por: Yu, Qinkai, et al.
Publicado: (2025)

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
por: Shao, Shuo, et al.
Publicado: (2024)

Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis
por: Zhu, Ziquan, et al.
Publicado: (2026)

Leveraging Persistence Image to Enhance Robustness and Performance in Curvilinear Structure Segmentation
por: Gao, Zhuangzhi, et al.
Publicado: (2026)

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

Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features
por: Zhu, Linghui, et al.
Publicado: (2025)

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
por: Sun, Ming, et al.
Publicado: (2026)

Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?
por: Xie, Jianyang, et al.
Publicado: (2025)

Under-confidence Backdoors Are Resilient and Stealthy Backdoors
por: Peng, Minlong, et al.
Publicado: (2022)

CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
por: Li, Yiming, et al.
Publicado: (2025)

Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities
por: Tang, Hua, et al.
Publicado: (2024)

Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach
por: Liao, Yifan, et al.
Publicado: (2025)

Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors
por: Lin, Tao, et al.
Publicado: (2024)

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
por: Wang, Xiaobao, et al.
Publicado: (2025)

BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
por: Liang, Siyuan, et al.
Publicado: (2026)

Formal Verification of Robustness and Resilience of Learning-Enabled State Estimation Systems
por: Huang, Wei, et al.
Publicado: (2020)

Harmless Backdoor-based Client-side Watermarking in Federated Learning
por: Luo, Kaijing, et al.
Publicado: (2024)

StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization
por: Tang, Yiming, et al.
Publicado: (2025)

BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
por: Guo, Ji, et al.
Publicado: (2025)

SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
por: Wang, Yingjia, et al.
Publicado: (2025)

Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifier
por: Jin, Gaojie, et al.
Publicado: (2025)