Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic

arXiv:2511.18660 · cs.LG, stat.ML · Submitted 2025-11-24 · Read on arXiv

cs.LG, stat.ML

Submitted: 2025-11-24

Updated: 2025-11-25

Code: https://github.com/mosix11/CUTS

Terminology

• Poison Trigger — 22× in this paper
• Machine Unlearning — 18× in this paper · explained in 2 episodes
• Fine-Tuning — 17× in this paper · explained in 5 episodes
• Symmetric Label Noise — 16× in this paper
• Accuracy — 12× in this paper · explained in 1 episode
• Corrective Machine Unlearning — 11× in this paper
• Cosine Similarity — 7× in this paper · explained in 3 episodes
• Generalization — 6× in this paper · explained in 13 episodes
• Asymmetric Label Noise — 5× in this paper
• Regularization — 5× in this paper · explained in 3 episodes
• Catastrophic Forgetting — 4× in this paper · explained in 5 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Corrective Unlearning in Task Space — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Additivity — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• In IEEE Symposium on Security and Privacy — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks