Cover Image

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Sanghyun, Carlini, Nicholas, Kurakin, Alexey
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
by: Shpilevskiy, Frederick, et al.
Published: (2025)

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
by: Nguyen, Quang H., et al.
Published: (2024)

Certified Robustness to Data Poisoning in Gradient-Based Training
by: Sosnin, Philip, et al.
Published: (2024)

Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
by: Deng, Jieren, et al.
Published: (2024)

Certifiably Robust Image Watermark
by: Jiang, Zhengyuan, et al.
Published: (2024)

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
by: Lin, Miao, et al.
Published: (2026)

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
by: Jang, Suhyeok, et al.
Published: (2024)

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
by: Souri, Hossein, et al.
Published: (2024)

LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning
by: Li, Beichen, et al.
Published: (2024)

Certified but Fooled! Breaking Certified Defences with Ghost Certificates
by: Vo, Quoc Viet, et al.
Published: (2025)

COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks
by: Huang, Zijian, et al.
Published: (2024)

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs
by: Yang, Yuchen, et al.
Published: (2024)

PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction
by: Wadekar, Prajas, et al.
Published: (2026)

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
by: Jacob, Dennis, et al.
Published: (2025)

Energy-Latency Attacks via Sponge Poisoning
by: Cinà, Antonio Emanuele, et al.
Published: (2022)

Delta-Influence: Unlearning Poisons via Influence Functions
by: Li, Wenjie, et al.
Published: (2024)

Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms
by: Villani, Francesco, et al.
Published: (2024)

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
by: Zhuang, Haomin, et al.
Published: (2023)

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

Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
by: Yu, Daiwei, et al.
Published: (2024)

Generalizable Targeted Data Poisoning against Varying Physical Objects
by: Chen, Zhizhen, et al.
Published: (2024)

Beyond Full Poisoning: Effective Availability Attacks with Partial Perturbation
by: Zhe, Yu, et al.
Published: (2024)

DiffBreak: Is Diffusion-Based Purification Robust?
by: Kassis, Andre, et al.
Published: (2024)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
by: He, Yuhao, et al.
Published: (2024)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
by: Zhang, Jinghuai, et al.
Published: (2022)

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
by: Li, Wenda, et al.
Published: (2024)

Robust Classification via a Single Diffusion Model
by: Chen, Huanran, et al.
Published: (2023)

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
by: Wang, Hao, et al.
Published: (2024)

ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
by: Yao, Xin, et al.
Published: (2025)

DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal
by: Shi, Jiaeli, et al.
Published: (2023)

Agnostic Multi-Robust Learning Using ERM
by: Ahmadi, Saba, et al.
Published: (2023)

Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
by: Gu, Hanlin, et al.
Published: (2024)

DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning Detection
by: Aboutalebi, Hossein, et al.
Published: (2023)

Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget
by: Yang, Yi, et al.
Published: (2026)

Toward Robust Non-Transferable Learning: A Survey and Benchmark
by: Hong, Ziming, et al.
Published: (2025)

MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
by: Ha, Hyeonjeong, et al.
Published: (2025)

Federated Learning with Label-Masking Distillation
by: Lu, Jianghu, et al.
Published: (2024)

Poison-splat: Computation Cost Attack on 3D Gaussian Splatting
by: Lu, Jiahao, et al.
Published: (2024)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
by: Wen, Yuxin, et al.
Published: (2024)

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
by: Wang, Yanbo, et al.
Published: (2024)