Cover Image

Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Yifan, Miao, Yibo, Dong, Yinpeng, Gao, Xiao-Shan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
by: Cao, Yichuan, et al.
Published: (2025)

T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
by: Miao, Yibo, et al.
Published: (2024)

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
by: Cheng, Shuyu, et al.
Published: (2024)

ARMOR: Shielding Unlearnable Examples against Data Augmentation
by: Gong, Xueluan, et al.
Published: (2025)

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
by: Liu, Shuang, et al.
Published: (2025)

Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability
by: Yu, Lijia, et al.
Published: (2025)

Scale-up Unlearnable Examples Learning with High-Performance Computing
by: Zhu, Yanfan, et al.
Published: (2025)

Toward Availability Attacks in 3D Point Clouds
by: Zhu, Yifan, et al.
Published: (2024)

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
by: Wang, Bo, et al.
Published: (2026)

Game-Theoretic Unlearnable Example Generator
by: Liu, Shuang, et al.
Published: (2024)

Generalizability of Memorization Neural Networks
by: Yu, Lijia, et al.
Published: (2024)

A Survey on Unlearnable Data
by: Li, Jiahao, et al.
Published: (2025)

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders
by: Yu, Yi, et al.
Published: (2024)

How Far Are We from True Unlearnability?
by: Ye, Kai, et al.
Published: (2025)

Towards a Novel Perspective on Adversarial Examples Driven by Frequency
by: Zhang, Zhun, et al.
Published: (2024)

Alignment Dynamics in LLM Fine-Tuning
by: Huang, Yuhan, et al.
Published: (2026)

Fairness in Survival Analysis: A Novel Conditional Mutual Information Augmentation Approach
by: Xie, Tianyang, et al.
Published: (2025)

Why Do Language Model Agents Whistleblow?
by: Agrawal, Kushal, et al.
Published: (2025)

Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
by: Liu, Jinlin, et al.
Published: (2026)

SoK: Unlearnability and Unlearning for Model Dememorization
by: Zhang, Mengying, et al.
Published: (2026)

Mutual Information Regularized Offline Reinforcement Learning
by: Ma, Xiao, et al.
Published: (2022)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
by: Zhu, Yunqin, et al.
Published: (2026)

Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
by: Sharma, Jai, et al.
Published: (2026)

Why Does RLAIF Work At All?
by: Young, Robin
Published: (2026)

Provably Unlearnable Data Examples
by: Wang, Derui, et al.
Published: (2024)

The Scaling Law for LoRA Base on Mutual Information Upper Bound
by: Zhang, Jing, et al.
Published: (2025)

DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal models
by: Blöbaum, Patrick, et al.
Published: (2022)

IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Prediction
by: Zhou, Yifan, et al.
Published: (2025)

Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical Perspective
by: Zhang, Yi-Ge, et al.
Published: (2025)

Unlearnable Examples For Time Series
by: Jiang, Yujing, et al.
Published: (2024)

Why Transformers Need Adam: A Hessian Perspective
by: Zhang, Yushun, et al.
Published: (2024)

Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
by: Miao, Yibo, et al.
Published: (2023)

Why Do Transformers Fail to Forecast Time Series In-Context?
by: Zhou, Yufa, et al.
Published: (2025)

Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
by: Zhao, Yike, et al.
Published: (2026)

Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control
by: Lawrence, Nathan P., et al.
Published: (2025)

Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models
by: Tian, Bowei, et al.
Published: (2025)

Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
by: Li, Simin, et al.
Published: (2023)

MMG: Mutual Information Estimation via the MMSE Gap in Diffusion
by: Yu, Longxuan, et al.
Published: (2025)

A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
by: Lee, Kyungeun, et al.
Published: (2024)

Why Do Time Series Models Need Long Context Windows?
by: Butera, Luca, et al.
Published: (2026)