The paper introduces inLoRA-MINT, an extension of the LoRA-MINT framework that uses intermediate model representations—such as activations and parameter-dependent signals—to perform Membership Inference Tests on large language models fine‑tuned with LoRA. By leveraging these representations, the method can distinguish training from non‑training samples without full parameter access, achieving 95–98% accuracy across four LLMs (Qwen, Phi‑4, DeepSeek‑V3, LLaMA 3.2‑3B) on medical, mathematical, and academic reasoning datasets. The approach offers a scalable way to audit sensitive training data and supports compliance with emerging privacy and AI governance regulations.
arXiv:2606. 06946v1 Announce Type: cross Abstract: We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA).
arXiv:2606. 17464v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties.
arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.
arXiv:2606. 14748v1 Announce Type: cross Abstract: We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes.
arXiv:2605.24614v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether...
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.
arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remains an open challenge.
arXiv:2606. 16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
arXiv:2602. 18934v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used during training.
arXiv:2610.10358v2 Announce Type: replace Abstract: As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pre...
The paper examines privacy risks in large language models (LLMs) through a unified threat model and systematic ablation study of four attacks: Membership Inference, Attribute Inference, Data Extraction, and Backdoor Attacks. It finds that membership inference is highly sensitive to dataset and attack strategy, attribute inference depends on model and training characteristics, data extraction grows with model size and repeated training data, and backdoor attacks consistently succeed. The authors provide practical recommendations for privacy‑aware LLM deployment, such as prioritizing membership leakage checks in retrieval‑augmented systems, reducing repeated personal data in training, monitoring attribute inference, and protecting fine‑tuning pipelines from backdoors.