Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility
Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as training data extraction (TDE) attacks can expose highly confidential information. Existing defenses against such attacks either lack formal privacy guarantees or incur substantial utility degradation. We observe that fine-tuning induces widespread probability shifts, yet preserving only a small subset of influential token-level deviations is sufficient; the remaining shifts can be aggressively smoothed with minimal impact on utility. Motivated by this insight, we propose SCP-$Δ_r$, a Near Access Freeness (NAF)-based algorithm that operates on relative probabilities and explicitly smooths low-impact tokens using a base model. SCP-$Δ_r$ achieves orders-of-magnitude better theoretical bounds than existing NAF based methods and provides strong empirical protection against TDE attacks with minimal performance loss.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy c…
QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals
Weight-only quantization is important for compressing Large Language Models (LLMs). Inspired by the spirit of classical magnitude pruning, we study whether the magnitude of weight updates during reasoning-incentivized fi…
Reinforcement LearningTemporal SequencesA Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but…
Binary ClassificationMixture-of-ExpertsLearning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning
The performance of finetuned large language models (LLMs) hinges critically on the composition of the training mixture. However, selecting an optimal blend of task datasets remains a largely manual, heuristic driven proc…
DiversityMMLUProvably Confidential Language Modelling
Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, e…
Language ModellingMemorizationText Generation