Imagen de Portada

Exact Certification of Data-Poisoning Attacks Using Mixed-Integer Programming

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sosnin, Philip, Knapp, Jodie, Kennedy, Fraser, Collyer, Josh, Tsay, Calvin
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy
por: Sosnin, Philip, et al.
Publicado: (2025)

Scaling Mixed-Integer Programming for Certification of Neural Network Controllers Using Bounds Tightening
por: Sosnin, Philip, et al.
Publicado: (2024)

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

Provably Safe Model Updates
por: Elmecker-Plakolm, Leo, et al.
Publicado: (2025)

Certification for Differentially Private Prediction in Gradient-Based Training
por: Wicker, Matthew, et al.
Publicado: (2024)

Relaxation-Informed Training of Neural Network Surrogate Models
por: Tsay, Calvin
Publicado: (2026)

Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense
por: Childress, Victoria, et al.
Publicado: (2025)

Training Neural ODEs Using Fully Discretized Simultaneous Optimization
por: Shapovalova, Mariia, et al.
Publicado: (2025)

Exact Certification of (Graph) Neural Networks Against Label Poisoning
por: Sabanayagam, Mahalakshmi, et al.
Publicado: (2024)

Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
por: Mohgaonkar, Ajinkya, et al.
Publicado: (2026)

Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
por: Liu, Shijie, et al.
Publicado: (2023)

Bayesian optimization as a flexible and efficient design framework for sustainable process systems
por: Paulson, Joel A., et al.
Publicado: (2024)

OTLP: Output Thresholding Using Mixed Integer Linear Programming
por: Koseoglu, Baran, et al.
Publicado: (2024)

Exact Graph Learning via Integer Programming
por: Kook, Lucas, et al.
Publicado: (2026)

Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming
por: Le, Tung Quoc, et al.
Publicado: (2026)

P-split formulations: A class of intermediate formulations between big-M and convex hull for disjunctive constraints
por: Kronqvist, Jan, et al.
Publicado: (2022)

Global Optimization of Gaussian Process Acquisition Functions Using a Piecewise-Linear Kernel Approximation
por: Xie, Yilin, et al.
Publicado: (2024)

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
por: Li, Jiate, et al.
Publicado: (2025)

Towards Foundation Models for Mixed Integer Linear Programming
por: Li, Sirui, et al.
Publicado: (2024)

Adversarial Bias: Data Poisoning Attacks on Fairness
por: Chan, Eunice, et al.
Publicado: (2025)

Mixed-Integer Programming for Change-point Detection
por: Narula, Apoorva, et al.
Publicado: (2026)

Towards Poisoning Robustness Certification for Natural Language Generation
por: Ghitu, Mihnea, et al.
Publicado: (2026)

Provable Watermarking for Data Poisoning Attacks
por: Zhu, Yifan, et al.
Publicado: (2025)

Are Targeted Data Poisoning Attacks as Effective as We Think?
por: Xu, William, et al.
Publicado: (2025)

When Deep Learning Meets Polyhedral Theory: A Survey
por: Huchette, Joey, et al.
Publicado: (2023)

A Distance Metric for Mixed Integer Programming Instances
por: Maudet, Gwen, et al.
Publicado: (2025)

Towards Certification of Uncertainty Calibration under Adversarial Attacks
por: Emde, Cornelius, et al.
Publicado: (2024)

MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
por: Lorenz, Tobias, et al.
Publicado: (2024)

Indiscriminate Data Poisoning Attacks on Neural Networks
por: Lu, Yiwei, et al.
Publicado: (2022)

Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
por: He, Longzhu, et al.
Publicado: (2025)

Generalized Optimal Classification Trees: A Mixed-Integer Programming Approach
por: Tu, Jiancheng, et al.
Publicado: (2026)

Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation
por: Edemacu, Kennedy, et al.
Publicado: (2025)

Mixing Vector Model for Copolymer Inference via Mixed Integer Linear Programming
por: Zhu, Jianshen, et al.
Publicado: (2026)

Machine Learning Algorithms for Improving Exact Classical Solvers in Mixed Integer Continuous Optimization
por: Kimiaei, Morteza, et al.
Publicado: (2025)

Predicting Accurate Lagrangian Multipliers for Mixed Integer Linear Programs
por: Demelas, Francesco, et al.
Publicado: (2023)

Modeling High-Dimensional Dependent Data in the Presence of Many Explanatory Variables and Weak Signals
por: Gao, Zhaoxing, et al.
Publicado: (2024)

SRG: Score-based Relaxation-guided Generation for Mixed Integer Linear Programming
por: Wang, Ruobing, et al.
Publicado: (2026)

Inverting Gradient Attacks Makes Powerful Data Poisoning
por: Bouaziz, Wassim, et al.
Publicado: (2024)

Taming Binarized Neural Networks and Mixed-Integer Programs
por: Aspman, Johannes, et al.
Publicado: (2023)

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