Imagen de Portada

Unlearning vs. Obfuscation: Are We Truly Removing Knowledge?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Guangzhi, Manakul, Potsawee, Zhan, Xiao, Gales, Mark
Formato:	Preprint
Publicado:	2025
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

SkillAggregation: Reference-free LLM-Dependent Aggregation
por: Sun, Guangzhi, et al.
Publicado: (2024)

Does Machine Unlearning Truly Remove Knowledge?
por: Chen, Haokun, et al.
Publicado: (2025)

Who can we trust? LLM-as-a-jury for Comparative Assessment
por: Qian, Mengjie, et al.
Publicado: (2026)

Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models
por: Manakul, Potsawee, et al.
Publicado: (2024)

Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge
por: Fathullah, Yassir, et al.
Publicado: (2025)

Towards Aligned Data Removal via Twin Machine Unlearning
por: Ji, Haoxuan, et al.
Publicado: (2024)

Are Expressive Models Truly Necessary for Offline RL?
por: Wang, Guan, et al.
Publicado: (2024)

Efficient Knowledge Graph Unlearning with Zeroth-order Information
por: Xiao, Yang, et al.
Publicado: (2025)

Graph Unlearning: Efficient Node Removal in Graph Neural Networks
por: Guan, Faqian, et al.
Publicado: (2025)

Fair Machine Unlearning: Data Removal while Mitigating Disparities
por: Oesterling, Alex, et al.
Publicado: (2023)

Probing Knowledge Holes in Unlearned LLMs
por: Ko, Myeongseob, et al.
Publicado: (2025)

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
por: Yang, Xiao, et al.
Publicado: (2025)

Fast Inference of Removal-Based Node Influence
por: Li, Weikai, et al.
Publicado: (2024)

Prior Prompt Engineering for Reinforcement Fine-Tuning
por: Taveekitworachai, Pittawat, et al.
Publicado: (2025)

Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
por: Pipatanakul, Kunat, et al.
Publicado: (2025)

Typhoon T1: An Open Thai Reasoning Model
por: Taveekitworachai, Pittawat, et al.
Publicado: (2025)

ROKA: Robust Knowledge Unlearning against Adversaries
por: Shin, Jinmyeong, et al.
Publicado: (2026)

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
por: Jang, Yeonwoo, et al.
Publicado: (2025)

When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?
por: Li, Chenyang, et al.
Publicado: (2025)

Large Language Models in Fire Engineering: An Examination of Technical Questions Against Domain Knowledge
por: Hostetter, Haley, et al.
Publicado: (2024)

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning
por: Bushipaka, Praveen, et al.
Publicado: (2025)

Federated Knowledge Graph Unlearning via Diffusion Model
por: Liu, Bingchen, et al.
Publicado: (2024)

Machine Unlearning in Low-Dimensional Feature Subspace
por: Fang, Kun, et al.
Publicado: (2026)

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
por: Chen, Zihan, et al.
Publicado: (2025)

Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models
por: Polowczyk, Agnieszka, et al.
Publicado: (2025)

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
por: Lin, Yujie, et al.
Publicado: (2026)

LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models
por: Liusie, Adian, et al.
Publicado: (2023)

Spatio-Temporal Graph Unlearning
por: Guo, Qiming, et al.
Publicado: (2025)

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
por: Hsu, Hsiang, et al.
Publicado: (2026)

Module-Aware Parameter-Efficient Machine Unlearning on Transformers
por: Bao, Wenjie, et al.
Publicado: (2025)

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

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
por: Yang, Puning, et al.
Publicado: (2026)

Unlink to Unlearn: Simplifying Edge Unlearning in GNNs
por: Tan, Jiajun, et al.
Publicado: (2024)

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
por: Taufeeque, Mohammad, et al.
Publicado: (2026)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
por: Cadet, Xavier F., et al.
Publicado: (2024)

CoLiDR: Concept Learning using Aggregated Disentangled Representations
por: Sinha, Sanchit, et al.
Publicado: (2024)

Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
por: Xiong, Guangzhi, et al.
Publicado: (2026)

ProtoNAM: Prototypical Neural Additive Models for Interpretable Deep Tabular Learning
por: Xiong, Guangzhi, et al.
Publicado: (2024)

Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detection
por: Li, Zhong, et al.
Publicado: (2025)

DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs
por: Mahmud, Tamim Al, et al.
Publicado: (2025)