The paper introduces Dynamic DAE Guardrails (DSG), a method that uses Dynamic Sparse Autoencoders to perform precision unlearning in large language models. DSG leverages principled feature selection and a dynamic classifier to target activation-based unlearning, outperforming existing gradient‑based methods in terms of computational efficiency, stability, sequential unlearning, resistance to relearning attacks, data efficiency, and interpretability.
arXiv:2609.16229v1 Announce Type: new Abstract: Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modify...
arXiv:2607. 11975v1 Announce Type: cross Abstract: Current machine unlearning methods predominantly rely on global, coarse-grained intervention strategies.
The paper presents a fast machine unlearning method that uses Hessian analysis to identify correlated training data and applies a closed‑form update rule. This approach achieves an 82× speedup over traditional influence‑function unlearning while maintaining or slightly improving model accuracy. Experiments on seven dataset‑architecture pairs, including CIFAR‑100 with ResNet‑50, show strong forgetting performance and low vulnerability to membership inference attacks.
The paper introduces Forgetting Only What Matters via Unlearning Layers (FOM-UL), a layer‑selective unlearning framework for large language models. FOM-UL uses a forget‑to‑retain significance score to identify transformer layers that strongly influence the forget set while being insensitive to the retain set, allowing targeted updates that preserve most of the model. Experiments on TOFU, KnowUnDo, and MUSE-style benchmarks show that FOM-UL reduces residual memorization and maintains utility better than several baselines, even after 8‑bit and 4‑bit post‑training quantization, and it also limits recovery of forgotten content in adversarial prompt tests.
The paper introduces Fast Preemptive Robustification (FPR), a lightweight defense that enhances the robustness of deep neural networks against transferable adversarial attacks. By sharpening Laplacian responses through a single 3×3 channel‑wise convolution, FPR eliminates the need for surrogate models, iterative optimization, or specialized training. Experiments show that FPR lowers untargeted attack success rates by 12.7% and reduces targeted attack success from 10.7% to 4.1%.
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
arXiv:2506. 07691v2 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability.
arXiv:2608. 05783v1 Announce Type: cross Abstract: Machine unlearning has become a critical capability for safely removing specific, sensitive knowledge from large language models (LLMs).
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whet...
arXiv:2607. 02513v1 Announce Type: cross Abstract: LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods.
The paper presents a robust approximate unlearning method for Generalized Learning Vector Quantization (GLVQ) classifiers, enabling the removal of specific data samples from trained models. It evaluates how the size and characteristics of the forget set affect unlearning, proposes an adapted technique to mitigate instabilities, and demonstrates that the method achieves near-zero deviation from a fully retrained model while being up to 10^5 times more efficient on benchmark tabular datasets. The approach is applicable to any GLVQ model without altering its training scheme.