Spectral unlearning applies matrix-structured updates to transformers
Applied atop existing objectives, it narrows most of the gap to a retain-trained reference on memorization, privacy, and utility.
Stories per day · 30 days
3 RSS
Relatedprivacy4split-learning2banking771batch-normalization1benchmarks1concept-erasure1decision-models1diffusion-models1edge-devices1edge-learning1federated-learning1language-models1model-snapshots1sdxl1sparse-autoencoders1text-reconstruction1trace1transformers1
14 stories, newest first · one card per story
Stories tagged #machine-unlearning
DecisionUnlearn-Bench measures unlearning when decision schemas change
On BANKING77, full-to-oracle displacement rose from example deletion to class deletion across 20 configurations.
Paper formulates split federated unlearning and proposes SURE
SURE uses dual-importance estimation and selective perturbation, matching retraining at modest extra cost.
BatchNorm buffers can fake deletion in split-learning unlearning
CIFAR-10 forget accuracy fell 61.50 points from BN recalibration with every learnable weight fixed.
ConceptACP erases diffusion concepts with sparse autoencoders
On SDXL-Turbo one-step generation, forgetting success rises 36.34 points over the best baseline.
TRACE reconstructs unlearned LLM text from pre- and post-unlearning snapshots
The attack needs no data-specific prior and was tested on TOFU, MUSE, and WMDP with six unlearning methods.
Why Forget-Only Unlearning Needs Memorization
A theory paper shows forget-only machine unlearning can require memorizing far more training data than ordinary learning keeps.
SOUL unlearning reduces state hallucination in robot VLA policies
The method forgets hallucination-linked sparse features while retaining successful manipulation behavior in simulation and real robots.
UnAct: Gradient-Free Unlearning via Targeted Activation Intervention
UnAct forgets classes with forward passes only and stays close to retraining when data is scarce.
Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning
A 174-language benchmark shows LLM unlearning fails across languages, and COVER improves cross-lingual erasure.
Data Unlearning via Inverse Distillation
Inverse Distillation Unlearning distills diffusion and flow models into one-step generators while suppressing a designated forget set.
ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control
ForgetMimic unlearns selected humanoid motions on Unitree robots while keeping other behaviors.
Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
Researchers introduce FOM-UL, a layer-selective machine unlearning framework that improves forgetting-utility trade-offs and resists knowledge recovery after quantization.
Machine Unlearning as Private Retroactive Algorithms
A cs.CR paper defines private retroactive algorithms, showing machine unlearning is a data-maintenance problem and giving DP constructions for linear statistics, clustering, histograms.