No article text was recorded for this version.
unlearning robustness
Version 2 of 2194 papers248 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Jogging the Memory of Unlearned Models Through Targeted Relearning Attacks
- Blog: An Adversarial Perspective on Machine Unlearning for AI Safety
- Blog: Rethinking Machine Unlearning in Image Generation Models
- Blog: Elastic Robust Unlearning of Specific Knowledge in Large Language Models
- Blog: The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
- Blog: Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
- Blog: Rethinking machine unlearning for large language models
- Blog: Rethinking machine unlearning for large language models
- Blog: BrainWash: A Poisoning Attack to Forget in Continual Learning
- Blog: Fairness and Robustness in Machine Unlearning
- Blog: RepSelect: Robust LLM Unlearning via Representational Selectivity
- Blog: Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models
- Blog: Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs
- Blog: Does Multimodal Large Language Model Truly Unlearn? Stealthy MLLM Unlearning Attack
- Blog: UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
- Blog: Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
- Blog: LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
- Blog: ReLearn: Unlearning via Learning for Large Language Models
- Blog: Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
- Blog: Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models
- Blog: Modular Pretraining Enables Access Control
- Blog: FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning
- Blog: A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
- Blog: When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
- Blog: MUNBa: Machine Unlearning via Nash Bargaining
- Blog: Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport
- Blog: A Comprehensive Survey on Visual Concept Mining in Text-to-image Diffusion Models
- Blog: Robust LLM Unlearning via Post Judgment and Multi-round Thinking
- Blog: Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
- Blog: A Unified Framework for Diffusion Model Unlearning with f-Divergence
- Blog: OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
- Blog: Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
- Blog: Dual-Space Smoothness for Robust and Balanced LLM Unlearning
- Blog: UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models
- Blog: Rethinking Machine Unlearning for Large Language Models
- Blog: Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models
- Blog: Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
- Blog: UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
- Blog: Large Language Model Unlearning for Source Code
- Blog: Erasing Conceptual Knowledge from Language Models
- Blog: UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
- Blog: SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
- Blog: ReLearn: Unlearning via Learning for Large Language Models
- Blog: Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
- Blog: Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
- Blog: Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
- Blog: Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
- Blog: Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
- Blog: A Survey of Machine Unlearning
- Blog: Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
- Blog: A General Framework to Enhance Fine-tuning-based LLM Unlearning
- Blog: Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
- Blog: No More, No Less: Least-Privilege Language Models
- Blog: Selective Fine-Tuning for Targeted and Robust Concept Unlearning
- Blog: Poisoning Attacks and Defenses to Federated Unlearning
- Blog: LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
- Blog: A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction
- Blog: Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
- Blog: Understanding Empirical Unlearning with Combinatorial Interpretability
- Blog: Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning
Showing 60 of 194 papers.
History & citation
Current · Permanent link
- Flattening the Loss Landscape for Resilient Machine Unlearning merged into this direction (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_unlearning_robustness_05459f5c,
title = {unlearning robustness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unlearning-robustness/rdr_05459f5cc34940eaaab1384b613d2bec},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_unlearning_robustness_05459f5c_v2,
title = {unlearning robustness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unlearning-robustness/rdr_05459f5cc34940eaaab1384b613d2bec/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}