Copertina

Potion: Towards Poison Unlearning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Schoepf, Stefan, Foster, Jack, Brintrup, Alexandra
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Loss-Free Machine Unlearning
di: Foster, Jack, et al.
Pubblicazione: (2024)

Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening
di: Schoepf, Stefan, et al.
Pubblicazione: (2024)

Identifying contributors to supply chain outcomes in a multi-echelon setting: a decentralised approach
di: Schoepf, Stefan, et al.
Pubblicazione: (2023)

An Information Theoretic Approach to Machine Unlearning
di: Foster, Jack, et al.
Pubblicazione: (2024)

Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization
di: Foster, Jack, et al.
Pubblicazione: (2023)

ConDa: Fast Federated Unlearning with Contribution Dampening
di: Chundawat, Vikram S, et al.
Pubblicazione: (2024)

Random Walk Guided Hyperbolic Graph Distillation
di: Long, Yunbo, et al.
Pubblicazione: (2025)

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
di: Schoepf, Stefan, et al.
Pubblicazione: (2025)

Using Reinforcement Learning for the Three-Dimensional Loading Capacitated Vehicle Routing Problem
di: Schoepf, Stefan, et al.
Pubblicazione: (2023)

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
di: Di, Jimmy Z., et al.
Pubblicazione: (2022)

Learning to Forget using Hypernetworks
di: Rangel, Jose Miguel Lara, et al.
Pubblicazione: (2024)

Evaluating Inter-Column Logical Relationships in Synthetic Tabular Data Generation
di: Long, Yunbo, et al.
Pubblicazione: (2025)

LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion
di: Long, Yunbo, et al.
Pubblicazione: (2025)

What if? Causal Machine Learning in Supply Chain Risk Management
di: Wyrembek, Mateusz, et al.
Pubblicazione: (2024)

Efficient and Privacy-Preserved Link Prediction via Condensed Graphs
di: Long, Yunbo, et al.
Pubblicazione: (2025)

Poisoning Attacks and Defenses to Federated Unlearning
di: Wang, Wenbin, et al.
Pubblicazione: (2025)

Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking
di: Jannelli, Valeria, et al.
Pubblicazione: (2024)

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery
di: Zhao, Wenwei, et al.
Pubblicazione: (2026)

Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning
di: Chang, Wenhan, et al.
Pubblicazione: (2024)

FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
di: Romandini, Nicolò, et al.
Pubblicazione: (2025)

Towards Poisoning Fair Representations
di: Liu, Tianci, et al.
Pubblicazione: (2023)

PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data
di: Long, Yunbo, et al.
Pubblicazione: (2025)

Topological Federated Clustering via Gravitational Potential Fields under Local Differential Privacy
di: Long, Yunbo, et al.
Pubblicazione: (2025)

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

TuneNSearch: a hybrid transfer learning and local search approach for solving vehicle routing problems
di: Corrêa, Arthur, et al.
Pubblicazione: (2025)

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

Machine Unlearning Fails to Remove Data Poisoning Attacks
di: Pawelczyk, Martin, et al.
Pubblicazione: (2024)

Towards Natural Machine Unlearning
di: He, Zhengbao, et al.
Pubblicazione: (2024)

Toward Efficient Data-Free Unlearning
di: Zhang, Chenhao, et al.
Pubblicazione: (2024)

Towards Source-Free Machine Unlearning
di: Ahmed, Sk Miraj, et al.
Pubblicazione: (2025)

Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training
di: Long, Yunbo, et al.
Pubblicazione: (2026)

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
di: Souly, Alexandra, et al.
Pubblicazione: (2025)

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

Towards Certified Unlearning for Deep Neural Networks
di: Zhang, Binchi, et al.
Pubblicazione: (2024)

Multi-Agent Digital Twinning for Collaborative Logistics: Framework and Implementation
di: Xu, Liming, et al.
Pubblicazione: (2023)

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
di: Wang, Qizhou, et al.
Pubblicazione: (2024)

Toward Reliable Machine Unlearning: Theory, Algorithms, and Evaluation
di: Ebrahimpour-Boroojeny, Ali
Pubblicazione: (2025)

Towards Reliable Testing of Machine Unlearning
di: Mazhar, Anna, et al.
Pubblicazione: (2026)

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness
di: Wang, Cheng-Long, et al.
Pubblicazione: (2024)

MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming
di: Schoepf, Stefan, et al.
Pubblicazione: (2025)