Image de couverture de livre

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hsu, Hsiang, Niroula, Pradeep, He, Zichang, Brugere, Ivan, Lecue, Freddy, Chen, Chun-Fu
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment
par: Hsu, Hsiang, et autres
Publié: (2026)

Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge
par: Lee, Seongmin, et autres
Publié: (2024)

The Effect of Data Poisoning on Counterfactual Explanations
par: Artelt, André, et autres
Publié: (2024)

On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
par: Ge, Zichang, et autres
Publié: (2025)

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
par: Zhang, Jiawei, et autres
Publié: (2024)

Machine Unlearning under Overparameterization
par: Block, Jacob L., et autres
Publié: (2025)

Interpreting Language Reward Models via Contrastive Explanations
par: Jiang, Junqi, et autres
Publié: (2024)

Does Privacy Always Harm Fairness? Data-Dependent Trade-offs via Chernoff Information Neural Estimation
par: Nichani, Arjun, et autres
Publié: (2026)

Auditing Approximate Machine Unlearning for Differentially Private Models
par: Gu, Yuechun, et autres
Publié: (2025)

Does Machine Unlearning Truly Remove Knowledge?
par: Chen, Haokun, et autres
Publié: (2025)

Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
par: Kariyappa, Sanjay, et autres
Publié: (2024)

Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs
par: Hamman, Faisal, et autres
Publié: (2024)

L2CU: Learning to Complement Unseen Users
par: Pitawela, Dileepa, et autres
Publié: (2026)

Machine Unlearning in Contrastive Learning
par: Wang, Zixin, et autres
Publié: (2024)

MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction
par: Martell, Marc Boubnovski, et autres
Publié: (2026)

Diffusion Model-Augmented Behavioral Cloning
par: Chen, Shang-Fu, et autres
Publié: (2023)

Machine Unlearning for Image-to-Image Generative Models
par: Li, Guihong, et autres
Publié: (2024)

DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks
par: Chen, Zhiliang, et autres
Publié: (2025)

Adaptive-lambda Subtracted Importance Sampled Scores in Machine Unlearning for DDPMs and VAEs
par: Dini, MohammadParsa, et autres
Publié: (2025)

Forecasting Unseen Points of Interest Visits Using Context and Proximity Priors
par: Li, Ziyao, et autres
Publié: (2024)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
par: Cadet, Xavier F., et autres
Publié: (2024)

Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access
par: Veldanda, Akshaj Kumar, et autres
Publié: (2023)

Feature-Selective Representation Misdirection for Machine Unlearning
par: Chen, Taozhao, et autres
Publié: (2025)

EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate Unlearning
par: Wang, Weiqi, et autres
Publié: (2026)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
par: Wang, Bin, et autres
Publié: (2026)

Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
par: Han, Ling, et autres
Publié: (2024)

Debiasing Machine Unlearning with Counterfactual Examples
par: Chen, Ziheng, et autres
Publié: (2024)

Efficient Machine Unlearning via Influence Approximation
par: Liu, Jiawei, et autres
Publié: (2025)

Machine Unlearning via Null Space Calibration
par: Chen, Huiqiang, et autres
Publié: (2024)

Knowledge-Aware Neuron Interpretation for Scene Classification
par: Guan, Yong, et autres
Publié: (2024)

Threats, Attacks, and Defenses in Machine Unlearning: A Survey
par: Liu, Ziyao, et autres
Publié: (2024)

Machine Unlearning: Solutions and Challenges
par: Xu, Jie, et autres
Publié: (2023)

Group-robust Machine Unlearning
par: De Min, Thomas, et autres
Publié: (2025)

A Survey of Machine Unlearning
par: Nguyen, Thanh Tam, et autres
Publié: (2022)

Soft Weighted Machine Unlearning
par: Qiao, Xinbao, et autres
Publié: (2025)

Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems
par: Li, Xiaochuan, et autres
Publié: (2025)

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
par: Huang, Tao, et autres
Publié: (2024)

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
par: Chen, Jiangwei, et autres
Publié: (2026)

Efficient Knowledge Deletion from Trained Models through Layer-wise Partial Machine Unlearning
par: Gogineni, Vinay Chakravarthi, et autres
Publié: (2024)

Probing Knowledge Holes in Unlearned LLMs
par: Ko, Myeongseob, et autres
Publié: (2025)