Cover Image

Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Min, Nay Myat, Pham, Long H., Sun, Jun
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models
by: Min, Nay Myat, et al.
Published: (2026)

CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models
by: Min, Nay Myat, et al.
Published: (2026)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, et al.
Published: (2025)

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
by: Li, Yige, et al.
Published: (2026)

Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
by: Shin, Jeongjin, et al.
Published: (2024)

SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
by: Wang, Yingjia, et al.
Published: (2025)

FFCBA: Feature-based Full-target Clean-label Backdoor Attacks
by: Yin, Yangxu, et al.
Published: (2025)

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
by: Wu, Zhixiao, et al.
Published: (2025)

Clean-Label Physical Backdoor Attacks with Data Distillation
by: Dao, Thinh, et al.
Published: (2024)

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
by: Kirci, Onur Alp, et al.
Published: (2025)

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
by: Zhi, Yuhan, et al.
Published: (2025)

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
by: Li, Yuetai, et al.
Published: (2024)

Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
by: Song, Baogang, et al.
Published: (2025)

A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
by: Dai, Jiazhu, et al.
Published: (2025)

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
by: Zeng, Yi, et al.
Published: (2024)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
by: Jiang, Peihai, et al.
Published: (2025)

Does Few-shot Learning Suffer from Backdoor Attacks?
by: Liu, Xinwei, et al.
Published: (2023)

Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents
by: Wang, Xuan, et al.
Published: (2025)

DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor Attack
by: Ma, Binhao, et al.
Published: (2023)

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
by: Qiu, Huming, et al.
Published: (2023)

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
by: Wang, Cheng-Long, et al.
Published: (2025)

ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
by: Alam, Manaar, et al.
Published: (2025)

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
by: Guo, Weiyang, et al.
Published: (2026)

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
by: Braun, Tobias, et al.
Published: (2026)

Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
by: Chen, Depeng, et al.
Published: (2024)

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
by: Zhao, Shuai, et al.
Published: (2024)

DUP: Detection-guided Unlearning for Backdoor Purification in Language Models
by: Hu, Man, et al.
Published: (2025)

Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
by: Li, Jianwei, et al.
Published: (2026)

In-Context Unlearning: Language Models as Few Shot Unlearners
by: Pawelczyk, Martin, et al.
Published: (2023)

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
by: Wu, Zongru, et al.
Published: (2024)

Robustifying Safety-Aligned Large Language Models through Clean Data Curation
by: Liu, Xiaoqun, et al.
Published: (2024)

CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks
by: Wu, Yinghao, et al.
Published: (2025)

Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models
by: Peng, Zuquan, et al.
Published: (2025)

MADE: Graph Backdoor Defense with Masked Unlearning
by: Lin, Xiao, et al.
Published: (2024)

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
by: Yu, Haiyang, et al.
Published: (2024)

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
by: Yu, Miao, et al.
Published: (2025)

When Forgetting Triggers Backdoors: A Clean Unlearning Attack
by: Arazzi, Marco, et al.
Published: (2025)

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
by: Min, Nay Myat, et al.
Published: (2024)

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
by: Zhu, Mingyan, et al.
Published: (2023)

Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
by: Fu, Anmin, et al.
Published: (2025)