Copertina

Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Xinrui, Geng, Chuanxing, Wan, Wenhai, Li, Shao-yuan, Chen, Songcan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
di: Wang, Xinrui, et al.
Pubblicazione: (2024)

Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning
di: Wang, Xinrui, et al.
Pubblicazione: (2025)

Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends
di: Wang, Xinrui, et al.
Pubblicazione: (2023)

Dynamic Against Dynamic: An Open-set Self-learning Framework
di: Yang, Haifeng, et al.
Pubblicazione: (2024)

Explicit View-labels Matter: A Multifacet Complementarity Study of Multi-view Clustering
di: Geng, Chuanxing, et al.
Pubblicazione: (2022)

LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
di: Geng, Chuanxing, et al.
Pubblicazione: (2025)

All-around Neural Collapse for Imbalanced Classification
di: Zhang, Enhao, et al.
Pubblicazione: (2024)

Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learning
di: Wan, Wenhai, et al.
Pubblicazione: (2023)

Pushing One Pair of Labels Apart Each Time in Multi-Label Learning: From Single Positive to Full Labels
di: Li, Xiang, et al.
Pubblicazione: (2023)

ULFine: Unbiased Lightweight Fine-tuning for Foundation-Model-Assisted Long-Tailed Semi-Supervised Learning
di: Zhang, Enhao, et al.
Pubblicazione: (2025)

A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trends
di: Li, Xiang, et al.
Pubblicazione: (2024)

Online Continual Learning with Dynamic Label Hierarchies
di: Wang, Xinrui, et al.
Pubblicazione: (2026)

Global Pre-fixing, Local Adjusting: A Simple yet Effective Contrastive Strategy for Continual Learning
di: Tang, Jia, et al.
Pubblicazione: (2025)

Backdoor or Manipulation? Graph Mixture of Experts Can Defend Against Various Graph Adversarial Attacks
di: Feng, Yuyuan, et al.
Pubblicazione: (2025)

Your Agent Can Defend Itself against Backdoor Attacks
di: Changjiang, Li, et al.
Pubblicazione: (2025)

PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning
di: Fan, Falong, et al.
Pubblicazione: (2025)

Invariant Aggregator for Defending against Federated Backdoor Attacks
di: Wang, Xiaoyang, et al.
Pubblicazione: (2022)

Defending against Backdoor Attack on Deep Neural Networks
di: Cheng, Hao, et al.
Pubblicazione: (2020)

Adaptive Federated Minimax Optimization with Lower Complexities
di: Huang, Feihu, et al.
Pubblicazione: (2022)

Defending Deep Regression Models against Backdoor Attacks
di: Du, Lingyu, et al.
Pubblicazione: (2024)

FedDefender: Backdoor Attack Defense in Federated Learning
di: Gill, Waris, et al.
Pubblicazione: (2023)

BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning
di: Zeng, Honghong, et al.
Pubblicazione: (2025)

CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
di: Mu, Fangwen, et al.
Pubblicazione: (2024)

Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
di: Obioma, Chibueze Peace, et al.
Pubblicazione: (2025)

No Regularization is Needed: An Efficient and Effective Model for Incomplete Label Distribution Learning
di: Li, Xiang, et al.
Pubblicazione: (2023)

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning
di: Wang, Yujing, et al.
Pubblicazione: (2024)

HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
di: Qiu, Pengyu, et al.
Pubblicazione: (2022)

Defending Against Poisoning Attacks in Federated Learning with Blockchain
di: Dong, Nanqing, et al.
Pubblicazione: (2023)

Instruction Backdoor Attacks Against Customized LLMs
di: Zhang, Rui, et al.
Pubblicazione: (2024)

InkDrop: Invisible Backdoor Attacks Against Dataset Condensation
di: Yang, He, et al.
Pubblicazione: (2026)

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
di: Liu, Shijie, et al.
Pubblicazione: (2025)

BadMerging: Backdoor Attacks Against Model Merging
di: Zhang, Jinghuai, et al.
Pubblicazione: (2024)

How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution
di: Wang, Jinbo, et al.
Pubblicazione: (2024)

Identifying the Truth of Global Model: A Generic Solution to Defend Against Byzantine and Backdoor Attacks in Federated Learning (full version)
di: Ebron, Sheldon C., et al.
Pubblicazione: (2023)

Defending Against Indirect Prompt Injection Attacks With Spotlighting
di: Hines, Keegan, et al.
Pubblicazione: (2024)

Multi-Target Backdoor Attacks Against Speaker Recognition
di: Fortier, Alexandrine, et al.
Pubblicazione: (2025)

Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
di: Chen, Xiangxiang, et al.
Pubblicazione: (2025)

MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training
di: Li, Jiacheng, et al.
Pubblicazione: (2023)

Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
di: Tan, Qi, et al.
Pubblicazione: (2024)

Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning
di: Assumpcao, Nicolas Riccieri Gardin, et al.
Pubblicazione: (2025)