12 articles tagged with #privacy-preservation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce RULER, a verification framework that detects machine unlearning failures at the representation level rather than just output metrics. The study reveals that popular unlearning methods pass traditional evaluation tests yet still retain encoded information about forgotten data in their internal representations, highlighting a critical gap in current verification protocols.
Researchers introduce FIT, a continual unlearning framework enabling large language models to efficiently forget privacy-sensitive, copyrighted, and harmful content across sequential deletion requests. The method addresses critical limitations of existing single-shot unlearning approaches by preventing catastrophic forgetting while maintaining model utility, demonstrated across models up to 14B parameters.
Researchers propose RPSG, a novel method for generating synthetic data from private text using large language models while maintaining differential privacy protections. The approach uses private seeds and formal privacy mechanisms during candidate selection, achieving high fidelity synthetic data with stronger privacy guarantees than existing methods.
Researchers discovered that privacy vulnerabilities in neural networks exist in only a small fraction of weights, but these same weights are critical for model performance. They developed a new approach that preserves privacy by rewinding and fine-tuning only these critical weights instead of retraining entire networks, maintaining utility while defending against membership inference attacks.
Researchers introduce Shadow Unlearning, a privacy-preserving machine unlearning method that removes training data influence from LLMs without exposing sensitive information to attacks. The Neuro-Semantic Projector Unlearning (NSPU) framework achieves this while maintaining model performance and is 10x more computationally efficient than existing approaches.
diffGHOST is a new conditional diffusion model that synthesizes mobility trajectories while preserving privacy through latent space segmentation. The approach addresses a critical gap in existing generative models that lack formal privacy guarantees despite handling sensitive personal movement data.
Researchers propose INO-SGD, a novel algorithm addressing the utility imbalance problem in individualized differential privacy (IDP) machine learning systems. The algorithm strategically down-weights sensitive data batches to prevent underrepresentation of privacy-protected subsets, improving model performance for high-privacy users while maintaining differential privacy guarantees.
Researchers introduce ICU-Bench, a new benchmark for testing machine unlearning in multimodal AI models, addressing privacy concerns from large-scale training datasets. The benchmark reveals that current unlearning methods struggle with continuous privacy deletion requests, highlighting a critical gap between theoretical approaches and real-world deployment needs.
Researchers propose a multi-objective unlearning framework for Large Language Models that simultaneously removes hazardous information, preserves general utility, avoids over-refusal, and resists adversarial attacks. The method uses unified domain representation and bidirectional logit distillation to harmonize competing optimization goals, achieving state-of-the-art performance across diverse unlearning requirements.
Researchers propose AdaProb, a machine unlearning method that enables trained AI models to efficiently forget specific data while preserving privacy and complying with regulations like GDPR. The approach uses adaptive probability distributions and demonstrates 20% improvement in forgetting effectiveness with 50% less computational overhead compared to existing methods.
Researchers propose FOUL (Federated On-server Unlearning), a new framework for efficiently removing specific participants' data from federated learning models without accessing client data. The approach reduces computational and communication costs while maintaining privacy compliance through a two-stage process that performs unlearning operations on the server side.
Researchers developed a method to train AI reasoning models to follow privacy instructions in their internal reasoning traces, not just final answers. The approach uses separate LoRA adapters and achieves up to 51.9% improvement on privacy benchmarks, though with some trade-offs in task performance.
