Image de couverture de livre

Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ho, Sy-Tuyen, Hao, Koh Jun, Nguyen, Ngoc-Bao, Binder, Alexander, Cheung, Ngai-Man
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks
par: Nguyen, Ngoc-Bao, et autres
Publié: (2025)

Model Inversion Robustness: Can Transfer Learning Help?
par: Ho, Sy-Tuyen, et autres
Publié: (2024)

On the Vulnerability of Skip Connections to Model Inversion Attacks
par: Koh, Jun Hao, et autres
Publié: (2024)

Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
par: Ho, Sy-Tuyen, et autres
Publié: (2025)

Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?
par: Tran, Viet-Hung, et autres
Publié: (2024)

Synth-Align: Improving Trustworthiness in Vision-Language Model with Synthetic Preference Data Alignment
par: Wijaya, Robert, et autres
Publié: (2024)

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI
par: Nguyen, Phat, et autres
Publié: (2025)

Evaluations of Machine Learning Privacy Defenses are Misleading
par: Aerni, Michael, et autres
Publié: (2024)

SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
par: Ho, Sy-Tuyen, et autres
Publié: (2026)

Urban Air Temperature Prediction using Conditional Diffusion Models
par: Dai, Siyang, et autres
Publié: (2024)

On the Adversarial Robustness of 3D Large Vision-Language Models
par: Liu, Chao, et autres
Publié: (2026)

Agentic Critical Training
par: Liu, Weize, et autres
Publié: (2026)

Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring
par: Nghiem, Huy, et autres
Publié: (2026)

Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems
par: Baattrup, Mads H., et autres
Publié: (2026)

A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
par: Abdollahzadeh, Milad, et autres
Publié: (2023)

One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
par: Le, Minh, et autres
Publié: (2025)

AIR: Zero-shot Generative Model Adaptation with Iterative Refinement
par: Liu, Guimeng, et autres
Publié: (2025)

Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection
par: Cao, Tri, et autres
Publié: (2024)

Misleading Microbenchmarks on the Java Virtual Machines
par: Schiavio, Filippo, et autres
Publié: (2026)

Frequency Masking for Universal Deepfake Detection
par: Doloriel, Chandler Timm, et autres
Publié: (2024)

Coverage-Validity-Aware Algorithmic Recourse
par: Bui, Ngoc, et autres
Publié: (2023)

Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimation
par: Starostin, Vladimir, et autres
Publié: (2024)

Sparse Partial Optimal Transport via Quadratic Regularization
par: Tran, Khang, et autres
Publié: (2025)

Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
par: Le, Minh, et autres
Publié: (2024)

Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios
par: Dang, Yunkai, et autres
Publié: (2024)

Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts
par: Le, Minh, et autres
Publié: (2025)

Learning Shortcuts: On the Misleading Promise of NLU in Language Models
par: Bihani, Geetanjali, et autres
Publié: (2024)

Inversion-Free Natural Gradient Descent on Riemannian Manifolds
par: Draca, Dario, et autres
Publié: (2026)

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them
par: Chen, Guanyu, et autres
Publié: (2025)

Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
par: Zhu, Dongxuan, et autres
Publié: (2026)

MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
par: Pham, Phu-Hoa, et autres
Publié: (2026)

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
par: Naseh, Ali, et autres
Publié: (2025)

Text to Image Generation and Editing: A Survey
par: Yang, Pengfei, et autres
Publié: (2025)

An Evaluation of LLMs Inference on Popular Single-board Computers
par: Tung, et autres
Publié: (2025)

Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleading
par: Crothers, Evan, et autres
Publié: (2023)

Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
par: Sy, Mohamed
Publié: (2026)

When Maximum Entropy Misleads Policy Optimization
par: Zhang, Ruipeng, et autres
Publié: (2025)

Controllable RANSAC-based Anomaly Detection via Hypothesis Testing
par: Phong, Le Hong, et autres
Publié: (2024)

Revisiting Hyperparameter Tuning with Differential Privacy
par: Ding, Youlong, et autres
Publié: (2022)

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations
par: Babadi, Narges, et autres
Publié: (2026)