Imagen de Portada

PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pooladzandi, Omead, Jiang, Jeffrey, Bhat, Sunay, Pottie, Gregory
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
por: Bhat, Sunay, et al.
Publicado: (2024)

PUREVQ-GAN: Defending Data Poisoning Attacks through Vector-Quantized Bottlenecks
por: Branch, Alexander, et al.
Publicado: (2025)

Curvature-Informed SGD via General Purpose Lie-Group Preconditioners
por: Pooladzandi, Omead, et al.
Publicado: (2024)

Implicit Bias and Convergence of Matrix Stochastic Mirror Descent
por: Akhtiamov, Danil, et al.
Publicado: (2026)

MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification
por: Gietz, Harrison, et al.
Publicado: (2024)

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
por: Joshi, Sunay, et al.
Publicado: (2025)

FlowPure: Continuous Normalizing Flows for Adversarial Purification
por: Collaert, Elias, et al.
Publicado: (2025)

Simulated Human Learning in a Dynamic, Partially-Observed, Time-Series Environment
por: Jiang, Jeffrey, et al.
Publicado: (2025)

Scaling Behavior of Discrete Diffusion Language Models
por: von Rütte, Dimitri, et al.
Publicado: (2025)

MidSteer: Optimal Affine Framework for Steering Generative Models
por: Gaintseva, Tatiana, et al.
Publicado: (2026)

On Transfer-based Universal Attacks in Pure Black-box Setting
por: Jalwana, Mohammad A. A. K., et al.
Publicado: (2025)

MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks
por: Karami, Mohammad, et al.
Publicado: (2025)

Robust Graph Learning Against Adversarial Evasion Attacks via Prior-Free Diffusion-Based Structure Purification
por: Luo, Jiayi, et al.
Publicado: (2025)

DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences
por: Feng, Chao, et al.
Publicado: (2025)

Foundations of Top-$k$ Decoding For Language Models
por: Noarov, Georgy, et al.
Publicado: (2025)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
por: Wang, Jiapeng, et al.
Publicado: (2026)

Towards Universal Neural Likelihood Inference
por: Brahmavar, Shreyas Bhat, et al.
Publicado: (2025)

LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs
por: Pal, Himanshu, et al.
Publicado: (2025)

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
por: Li, Donghao, et al.
Publicado: (2026)

The Effect of Data Poisoning on Counterfactual Explanations
por: Artelt, André, et al.
Publicado: (2024)

TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models
por: Kumar, Bhagyesh, et al.
Publicado: (2025)

Mathematical Formalism for Memory Compression in Selective State Space Models
por: Bhat, Siddhanth
Publicado: (2024)

In-Context Learning for Pure Exploration
por: Russo, Alessio, et al.
Publicado: (2025)

Intelligent Chemical Purification Technique Based on Machine Learning
por: Wu, Wenchao, et al.
Publicado: (2024)

ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
por: Xu, Zhangchen, et al.
Publicado: (2024)

Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
por: Yin, Xuwang, et al.
Publicado: (2025)

PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning
por: Liu, Tao, et al.
Publicado: (2026)

Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning
por: Zhou, Xue, et al.
Publicado: (2025)

In-Run Data Shapley for Adam Optimizer
por: Ding, Meng, et al.
Publicado: (2026)

Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics
por: Acharjee, Jashaswimalya, et al.
Publicado: (2026)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
por: Xu, Yinglun, et al.
Publicado: (2024)

Preference Poisoning Attacks on Reward Model Learning
por: Wu, Junlin, et al.
Publicado: (2024)

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
por: Zeng, Yirong, et al.
Publicado: (2025)

Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling
por: Balcerak, Michal, et al.
Publicado: (2025)

Energy-Based Models for Continual Learning
por: Li, Shuang, et al.
Publicado: (2020)

Adversarial Training for Defense Against Label Poisoning Attacks
por: Bal, Melis Ilayda, et al.
Publicado: (2025)

Perfect Alignment May be Poisonous to Graph Contrastive Learning
por: Liu, Jingyu, et al.
Publicado: (2023)

Peak-Controlled Logits Poisoning Attack in Federated Distillation
por: Tang, Yuhan, et al.
Publicado: (2024)

Universal Jailbreak Backdoors from Poisoned Human Feedback
por: Rando, Javier, et al.
Publicado: (2023)

Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision
por: Cui, Jiali, et al.
Publicado: (2026)