Image de couverture de livre

PUREVQ-GAN: Defending Data Poisoning Attacks through Vector-Quantized Bottlenecks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Branch, Alexander, Pooladzandi, Omead, Khosraviani, Radin, Bhat, Sunay Gajanan, Jiang, Jeffrey, Pottie, Gregory
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
par: Bhat, Sunay, et autres
Publié: (2024)

PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models
par: Pooladzandi, Omead, et autres
Publié: (2024)

Curvature-Informed SGD via General Purpose Lie-Group Preconditioners
par: Pooladzandi, Omead, et autres
Publié: (2024)

Style Quantization for Data-Efficient GAN Training
par: Wang, Jian, et autres
Publié: (2025)

SQ-GAN: Semantic Image Communications Using Masked Vector Quantization
par: Pezone, Francesco, et autres
Publié: (2025)

EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
par: Kim, Sangwon, et autres
Publié: (2024)

Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
par: Jiang, Shiyi, et autres
Publié: (2025)

VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise
par: He, Zhixun, et autres
Publié: (2024)

DataFreeShield: Defending Adversarial Attacks without Training Data
par: Lee, Hyeyoon, et autres
Publié: (2024)

Defending Against Frequency-Based Attacks with Diffusion Models
par: Amerehi, Fatemeh, et autres
Publié: (2025)

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
par: Zhou, Qi, et autres
Publié: (2024)

Backdoor Poisoning Attack Against Face Spoofing Attack Detection Methods
par: Iwamatsu, Shota, et autres
Publié: (2025)

SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
par: Du, Lingyu, et autres
Publié: (2025)

CSI4Free: GAN-Augmented mmWave CSI for Improved Pose Classification
par: Bhat, Nabeel Nisar, et autres
Publié: (2024)

Implicit Bias and Convergence of Matrix Stochastic Mirror Descent
par: Akhtiamov, Danil, et autres
Publié: (2026)

Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing
par: Li, Shuai, et autres
Publié: (2025)

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
par: Ishmam, Alvi Md, et autres
Publié: (2024)

One-Index Vector Quantization Based Adversarial Attack on Image Classification
par: Fan, Haiju, et autres
Publié: (2024)

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
par: Strack, Lukas, et autres
Publié: (2023)

Masked Vector Quantization
par: Nguyen, David D., et autres
Publié: (2023)

Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
par: Lee, Cheng-Yi, et autres
Publié: (2024)

Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression
par: Jiang, Shiyin, et autres
Publié: (2026)

IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields
par: Jiang, Wenxiang, et autres
Publié: (2024)

Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
par: Zhang, Wei, et autres
Publié: (2026)

SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack
par: Park, Junha, et autres
Publié: (2025)

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
par: Jang, Sangwon, et autres
Publié: (2025)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
par: Zhang, Jinghuai, et autres
Publié: (2022)

Adversarial Data Poisoning Attacks on Quantum Machine Learning in the NISQ Era
par: Kundu, Satwik, et autres
Publié: (2024)

FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization
par: Iftee, Md Akil Raihan, et autres
Publié: (2025)

Channel-wise Vector Quantization
par: Song, Wei, et autres
Publié: (2026)

Autoregressive Video Generation without Vector Quantization
par: Deng, Haoge, et autres
Publié: (2024)

Autoregressive Image Generation without Vector Quantization
par: Li, Tianhong, et autres
Publié: (2024)

Hierarchical Vector Quantization for Unsupervised Action Segmentation
par: Spurio, Federico, et autres
Publié: (2024)

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
par: Liang, Jiawei, et autres
Publié: (2024)

Time Traveling to Defend Against Adversarial Example Attacks in Image Classification
par: Etim, Anthony, et autres
Publié: (2024)

Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization
par: Lu, Hao, et autres
Publié: (2026)

Lightweight Road Environment Segmentation using Vector Quantization
par: Kwag, Jiyong, et autres
Publié: (2025)

SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting
par: Li, Shuaiting, et autres
Publié: (2025)

Vector-Quantized Soft Label Compression for Dataset Distillation
par: Abbasi, Ali, et autres
Publié: (2026)

Vector Quantization Prompting for Continual Learning
par: Jiao, Li, et autres
Publié: (2024)