Imagen de Portada

Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Nan, Yu, Haiyang, Yi, Ping
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Magnitude-based Neuron Pruning for Backdoor Defens
por: Li, Nan, et al.
Publicado: (2024)

OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection
por: Jiang, Haoyu, et al.
Publicado: (2023)

Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
por: Min, Rui, et al.
Publicado: (2024)

Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
por: Han, Tingxu, et al.
Publicado: (2024)

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
por: Ren, Zhiyao, et al.
Publicado: (2025)

Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space
por: Vyas, Sanyam, et al.
Publicado: (2024)

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
por: Wang, Yifei, et al.
Publicado: (2026)

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
por: Pal, Soumyadeep, et al.
Publicado: (2024)

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

PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
por: Li, Wei, et al.
Publicado: (2024)

Backdoor Graph Condensation
por: Wu, Jiahao, et al.
Publicado: (2024)

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
por: Lin, Weilin, et al.
Publicado: (2024)

Heterogeneous Graph Backdoor Attack
por: Chen, Jiawei, et al.
Publicado: (2025)

Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
por: Zhang, Yujie, et al.
Publicado: (2024)

Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses
por: Pawlak, Stanisław, et al.
Publicado: (2025)

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
por: An, Shengwei, et al.
Publicado: (2023)

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

Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions
por: Yang, Xiao, et al.
Publicado: (2024)

A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning
por: Gluch, Greg, et al.
Publicado: (2025)

Backdoor defense, learnability and obfuscation
por: Christiano, Paul, et al.
Publicado: (2024)

How to Backdoor the Knowledge Distillation
por: Wu, Chen, et al.
Publicado: (2025)

BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack
por: Khan, Md Nabi Newaz, et al.
Publicado: (2026)

Compromising Embodied Agents with Contextual Backdoor Attacks
por: Liu, Aishan, et al.
Publicado: (2024)

Fast and Lightweight Backdoor Detection via Head Random Probing
por: Yu, Yinbo, et al.
Publicado: (2026)

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
por: Mo, Yichuan, et al.
Publicado: (2024)

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

Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain
por: Huang, Yuanmin, et al.
Publicado: (2025)

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
por: Gong, Chen, et al.
Publicado: (2022)

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

How to Craft Backdoors with Unlabeled Data Alone?
por: Wang, Yifei, et al.
Publicado: (2024)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
por: Chen, Zhuowei, et al.
Publicado: (2025)

LoBAM: LoRA-Based Backdoor Attack on Model Merging
por: Yin, Ming, et al.
Publicado: (2024)

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation
por: Li, Jianwei, et al.
Publicado: (2026)

PBP: Post-training Backdoor Purification for Malware Classifiers
por: Nguyen, Dung Thuy, et al.
Publicado: (2024)

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
por: Pichler, Georg, et al.
Publicado: (2024)

BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
por: Lin, Xiao, et al.
Publicado: (2024)

Backdooring Bias ($B^2$) into Stable Diffusion Models
por: Naseh, Ali, et al.
Publicado: (2024)

Flatness-aware Sequential Learning Generates Resilient Backdoors
por: Pham, Hoang, et al.
Publicado: (2024)

Invisible Backdoor Attack Through Singular Value Decomposition
por: Chen, Wenmin, et al.
Publicado: (2024)

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
por: De Muri, Giovanni, et al.
Publicado: (2025)