Cover Image

From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	George, Daniel, Yeh, Charles, Lee, Daniel, Zhang, Yifei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Synthetic Iris Image Databases and Identity Leakage: Risks and Mitigation Strategies
by: Sawilska, Ada, et al.
Published: (2025)

Mitigating Cross-Image Information Leakage in LVLMs for Multi-Image Tasks
by: Park, Yeji, et al.
Published: (2025)

XNN: Paradigm Shift in Mitigating Identity Leakage within Cloud-Enabled Deep Learning
by: Liu, Kaixin, et al.
Published: (2024)

Fill the Gap: Quantifying and Reducing the Modality Gap in Image-Text Representation Learning
by: Role, François, et al.
Published: (2025)

Improving Image Restoration through Removing Degradations in Textual Representations
by: Lin, Jingbo, et al.
Published: (2023)

Only-Style: Stylistic Consistency in Image Generation without Content Leakage
by: Aravanis, Tilemachos, et al.
Published: (2025)

FaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction
by: Guo, Wenqi, et al.
Published: (2026)

Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection
by: Koutlis, Christos, et al.
Published: (2024)

Encoder-Only Image Registration
by: Chen, Xiang, et al.
Published: (2025)

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation
by: Song, Yizhi, et al.
Published: (2024)

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
by: Zhang, Shilong, et al.
Published: (2025)

Omni-ID: Holistic Identity Representation Designed for Generative Tasks
by: Qian, Guocheng, et al.
Published: (2024)

General Vision Encoder Features as Guidance in Medical Image Registration
by: Kögl, Fryderyk, et al.
Published: (2024)

Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities
by: Song, Peibo, et al.
Published: (2026)

LCM-Lookahead for Encoder-based Text-to-Image Personalization
by: Gal, Rinon, et al.
Published: (2024)

FlashFace: Human Image Personalization with High-fidelity Identity Preservation
by: Zhang, Shilong, et al.
Published: (2024)

Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration
by: Huang, Xinghua, et al.
Published: (2026)

Object Remover Performance Evaluation Methods using Class-wise Object Removal Images
by: Oh, Changsuk, et al.
Published: (2024)

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases
by: Tan, Shuai, et al.
Published: (2025)

Single Image Reflection Removal with Patch Reflectance Prior
by: Han, Dongshen, et al.
Published: (2023)

Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations
by: Anderson, Kathleen, et al.
Published: (2025)

Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation
by: Han, Jiawei, et al.
Published: (2024)

DenseSR: Image Shadow Removal as Dense Prediction
by: Lin, Yu-Fan, et al.
Published: (2025)

A Shared Encoder Approach to Multimodal Representation Learning
by: Roy, Shuvendu, et al.
Published: (2025)

Disentangling Latent Embeddings with Sparse Linear Concept Subspaces (SLiCS)
by: Li, Zhi, et al.
Published: (2025)

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders
by: Ryan, Fiona, et al.
Published: (2024)

Fusion to Enhance: Fusion Visual Encoder to Enhance Multimodal Language Model
by: She, Yifei, et al.
Published: (2025)

Non-negative Subspace Feature Representation for Few-shot Learning in Medical Imaging
by: Fan, Keqiang, et al.
Published: (2024)

SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation
by: Zhang, Yuxuan, et al.
Published: (2023)

Image Generation with a Sphere Encoder
by: Yue, Kaiyu, et al.
Published: (2026)

Text-Guided Semantic Image Encoder
by: Thirukovalluru, Raghuveer, et al.
Published: (2025)

The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models
by: Mao, Runhao, et al.
Published: (2026)

Learning Visual-Semantic Subspace Representations
by: Moreira, Gabriel, et al.
Published: (2024)

REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders
by: Khosla, Savya, et al.
Published: (2025)

Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
by: Yan, Zhiyuan, et al.
Published: (2024)

EvTurb: Event Camera Guided Turbulence Removal
by: Liu, Yixing, et al.
Published: (2025)

Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder
by: Zhang, Tianyu, et al.
Published: (2025)

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
by: Ventura, Mor, et al.
Published: (2025)

Addressing Text Embedding Leakage in Diffusion-based Image Editing
by: Mun, Sunung, et al.
Published: (2024)

Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
by: Herbreteau, Sébastien, et al.
Published: (2022)