Imagen de Portada

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Fei, Li, Baochun
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computation and Language Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Promoting Data and Model Privacy in Federated Learning through Quantized LoRA
por: Zhu, JianHao, et al.
Publicado: (2024)

Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning
por: Wang, Fei, et al.
Publicado: (2025)

Weight space Detection of Backdoors in LoRA Adapters
por: Merenciano, David Puertolas, et al.
Publicado: (2026)

LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
por: Ran, Delong, et al.
Publicado: (2025)

Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights
por: Yao, Dixi
Publicado: (2024)

Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption
por: Frery, Jordan, et al.
Publicado: (2025)

Colluding LoRA: A Compositional Vulnerability in LLM Safety Alignment
por: Ding, Sihao
Publicado: (2026)

MOLM: Mixture of LoRA Markers
por: Fares, Samar, et al.
Publicado: (2025)

Improving LoRA in Privacy-preserving Federated Learning
por: Sun, Youbang, et al.
Publicado: (2024)

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing
por: Chen, Jiahao, et al.
Publicado: (2025)

Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions
por: Liu, Jinxin, et al.
Publicado: (2024)

Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
por: Lan, Wenhao, et al.
Publicado: (2026)

Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment
por: Rad, Melissa Kazemi, et al.
Publicado: (2025)

Data-centric NLP Backdoor Defense from the Lens of Memorization
por: Wang, Zhenting, et al.
Publicado: (2024)

Localizing Paragraph Memorization in Language Models
por: Stoehr, Niklas, et al.
Publicado: (2024)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
por: Xiong, Alexander, et al.
Publicado: (2025)

CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistants
por: Noah, Amit Finkman, et al.
Publicado: (2024)

SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
por: Liu, Jianmin, et al.
Publicado: (2025)

LoBAM: LoRA-Based Backdoor Attack on Model Merging
por: Yin, Ming, et al.
Publicado: (2024)

Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models
por: Fu, Wenjie, et al.
Publicado: (2025)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
por: Yang, Qin, et al.
Publicado: (2024)

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
por: Liu, Hongyi, et al.
Publicado: (2024)

Position: Privacy Is Not Just Memorization!
por: Mireshghallah, Niloofar, et al.
Publicado: (2025)

ZKLoRA: Efficient Zero-Knowledge Proofs for LoRA Verification
por: Roy, Bidhan, et al.
Publicado: (2025)

Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
por: Joshi, Kunj, et al.
Publicado: (2025)

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
por: Ahn, Beomjin, et al.
Publicado: (2026)

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
por: Chua, Lynn, et al.
Publicado: (2024)

What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
por: Fan, Mingyuan, et al.
Publicado: (2026)

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
por: Hsiung, Lei, et al.
Publicado: (2025)

DMFI: A Dual-Modality Log Analysis Framework for Insider Threat Detection with LoRA-Tuned Language Models
por: Kong, Kaichuan, et al.
Publicado: (2025)

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
por: Labiad, Ismail, et al.
Publicado: (2025)

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
por: Xin, Rui, et al.
Publicado: (2025)

A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations
por: Liu, Zihan, et al.
Publicado: (2026)

LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
por: Huang, Yining, et al.
Publicado: (2025)

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
por: Guo, Wenkai, et al.
Publicado: (2025)

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning
por: Hasan, Adib, et al.
Publicado: (2024)

Revisiting the Robustness of Watermarking to Paraphrasing Attacks
por: Rastogi, Saksham, et al.
Publicado: (2024)

Rapid LoRA Aggregation for Wireless Channel Adaptation in Open-Set Radio Frequency Fingerprinting
por: Zhang, Mingxi, et al.
Publicado: (2026)

Secure LLM Fine-Tuning via Safety-Aware Probing
por: Wu, Chengcan, et al.
Publicado: (2025)

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
por: Wang, Zhepeng, et al.
Publicado: (2024)