Cover Image

Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Akbari, Ramin, Afshari, Milad, Boddeti, Vishnu Naresh
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shift
by: Sreekumar, Gautam, et al.
Published: (2025)

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
by: Dehdashtian, Sepehr, et al.
Published: (2024)

Utility-Fairness Trade-Offs and How to Find Them
by: Dehdashtian, Sepehr, et al.
Published: (2024)

OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes
by: Dehdashtian, Sepehr, et al.
Published: (2025)

DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows
by: Morshed, Mashrur M., et al.
Published: (2025)

Log-linear Guardedness and its Implications
by: Ravfogel, Shauli, et al.
Published: (2022)

CoInD: Enabling Logical Compositions in Diffusion Models
by: Gaudi, Sachit, et al.
Published: (2025)

Compositional World Knowledge leads to High Utility Synthetic data
by: Gaudi, Sachit, et al.
Published: (2025)

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors
by: Dehdashtian, Sepehr, et al.
Published: (2025)

Estimating Parameter Fields in Multi-Physics PDEs from Scarce Measurements
by: Li, Xuyang, et al.
Published: (2025)

Mechanics-Informed Autoencoder Enables Automated Detection and Localization of Unforeseen Structural Damage
by: Li, Xuyang, et al.
Published: (2024)

Nonlinear Concept Erasure: a Density Matching Approach
by: Saillenfest, Antoine, et al.
Published: (2025)

Kernelized Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)

Fundamental Limits of Perfect Concept Erasure
by: Chowdhury, Somnath Basu Roy, et al.
Published: (2025)

A Deep Learning Framework for Three Dimensional Shape Reconstruction from Phaseless Acoustic Scattering Far-field Data
by: Dikbayir, Doga, et al.
Published: (2024)

Linear Adversarial Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)

CryptoFace: End-to-End Encrypted Face Recognition
by: Ao, Wei, et al.
Published: (2025)

Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models
by: Russinovich, Mark, et al.
Published: (2025)

Minimalist Concept Erasure in Generative Models
by: Zhang, Yang, et al.
Published: (2025)

Forget Less by Learning Together through Concept Consolidation
by: Kaushik, Arjun Ramesh, et al.
Published: (2026)

Closed-Form Concept Erasure via Double Projections
by: Zhang, Chi, et al.
Published: (2026)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
by: Karvonen, Adam, et al.
Published: (2024)

Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm
by: Kim, Jaehan, et al.
Published: (2024)

Rethinking the Vulnerability of Concept Erasure and a New Method
by: Richardson, Alex D., et al.
Published: (2025)

Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
by: Braun, Tobias, et al.
Published: (2025)

Separable Multi-Concept Erasure from Diffusion Models
by: Zhao, Mengnan, et al.
Published: (2024)

TraSCE: Trajectory Steering for Concept Erasure
by: Jain, Anubhav, et al.
Published: (2024)

MACE: Mass Concept Erasure in Diffusion Models
by: Lu, Shilin, et al.
Published: (2024)

Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
by: Novello, Nicola, et al.
Published: (2026)

Minimal Communication-Cost Statistical Learning
by: Sefidgaran, Milad, et al.
Published: (2024)

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
by: Bui, Anh, et al.
Published: (2025)

TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes
by: Jourdan, Fanny, et al.
Published: (2023)

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
by: Kusumba, Abhiram, et al.
Published: (2025)

Improving Variational Autoencoder using Random Fourier Transformation: An Aviation Safety Anomaly Detection Case-Study
by: Asanjan, Ata Akbari, et al.
Published: (2026)

Learning for Bandits under Action Erasures
by: Hanna, Osama, et al.
Published: (2024)

Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
by: Chen, Hongxu, et al.
Published: (2025)

Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation
by: Kim, Yongwoo, et al.
Published: (2026)

CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
by: Xue, Yuyang, et al.
Published: (2025)

Does Feedback Help in Bandits with Arm Erasures?
by: Karakas, Merve, et al.
Published: (2025)

AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
by: Li, Fengpeng, et al.
Published: (2026)