Image de couverture de livre

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Bo, Ni, Jia, Zhao, Mengnan, Qin, Zhan, Ren, Kui
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ARMOR: Shielding Unlearnable Examples against Data Augmentation
par: Gong, Xueluan, et autres
Publié: (2025)

Provably Unlearnable Data Examples
par: Wang, Derui, et autres
Publié: (2024)

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
par: Zhao, Mengnan, et autres
Publié: (2026)

SoK: Unlearnability and Unlearning for Model Dememorization
par: Zhang, Mengying, et autres
Publié: (2026)

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders
par: Yu, Yi, et autres
Publié: (2024)

Game-Theoretic Unlearnable Example Generator
par: Liu, Shuang, et autres
Publié: (2024)

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
par: Shao, Shuo, et autres
Publié: (2024)

FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model
par: Shao, Shuo, et autres
Publié: (2022)

Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
par: Rajendran, Suraj, et autres
Publié: (2023)

NPAT Null-Space Projected Adversarial Training Towards Zero Deterioration
par: Hu, Hanyi, et autres
Publié: (2024)

PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking
par: Deng, Haiyu, et autres
Publié: (2025)

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise
par: Liu, Yixin, et autres
Publié: (2023)

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
par: Nguyen, Quang Duc, et autres
Publié: (2026)

PEAS: A Strategy for Crafting Transferable Adversarial Examples
par: Avraham, Bar, et autres
Publié: (2024)

CLASP: Training-Free LLM-Assisted Source Code Watermarking via Semantic-Preserving Transformations
par: Xu, Rui, et autres
Publié: (2025)

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
par: Duan, Kaiwen, et autres
Publié: (2025)

Privacy-preserving Decision-focused Learning for Multi-energy Systems
par: Zhou, Yangze, et autres
Publié: (2025)

Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
par: Fang, Junyuan, et autres
Publié: (2025)

Backdoor Detection through Replicated Execution of Outsourced Training
par: Jia, Hengrui, et autres
Publié: (2025)

The Autonomy Tax: Defense Training Breaks LLM Agents
par: Li, Shawn, et autres
Publié: (2026)

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
par: Gao, Junqi, et autres
Publié: (2024)

A Causal Perspective for Enhancing Jailbreak Attack and Defense
par: Pan, Licheng, et autres
Publié: (2026)

FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
par: Shao, Shuo, et autres
Publié: (2025)

Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion
par: Liu, Xuan, et autres
Publié: (2024)

DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection
par: Du, Xia, et autres
Publié: (2025)

What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift
par: Chang, Jiamin, et autres
Publié: (2025)

Reconstructing Training Data from Adapter-based Federated Large Language Models
par: Chen, Silong, et autres
Publié: (2026)

ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach
par: Hu, Yuke, et autres
Publié: (2023)

SurvAttack: Black-Box Attack On Survival Models through Ontology-Informed EHR Perturbation
par: Kerdabadi, Mohsen Nayebi, et autres
Publié: (2024)

A Novel Ensemble Learning Approach for Enhanced IoT Attack Detection: Redefining Security Paradigms in Connected Systems
par: Abdeljaber, Hikmat A. M., et autres
Publié: (2025)

T2UE: Generating Unlearnable Examples from Text Descriptions
par: Ma, Xingjun, et autres
Publié: (2025)

Mitigating Error Amplification in Fast Adversarial Training
par: Zhao, Mengnan, et autres
Publié: (2026)

A Novel Perturb-ability Score to Mitigate Evasion Adversarial Attacks on Flow-Based ML-NIDS
par: elShehaby, Mohamed, et autres
Publié: (2024)

Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
par: Yin, Yi, et autres
Publié: (2025)

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
par: Chen, Yukun, et autres
Publié: (2025)

Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Framework
par: Chen, Shengchao, et autres
Publié: (2024)

Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
par: Wang, Yisen, et autres
Publié: (2025)

AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
par: Qiu, Le, et autres
Publié: (2025)

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
par: Lu, Ning, et autres
Publié: (2025)

Nonlinear Transformations Against Unlearnable Datasets
par: Hapuarachchi, Thushari, et autres
Publié: (2024)