Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Goel, Anmol, Emde, Cornelius, Yun, Sangdoo, Oh, Seong Joon, Gubri, Martin
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MASEval: Extending Multi-Agent Evaluation from Models to Systems
by: Emde, Cornelius, et al.
Published: (2026)

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
by: Puerto, Haritz, et al.
Published: (2024)

Calibrating Large Language Models Using Their Generations Only
by: Ulmer, Dennis, et al.
Published: (2024)

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
by: Green, Tommaso, et al.
Published: (2025)

C-SEO Bench: Does Conversational SEO Work?
by: Puerto, Haritz, et al.
Published: (2025)

Dr.LLM: Dynamic Layer Routing in LLMs
by: Heakl, Ahmed, et al.
Published: (2025)

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
by: Gubri, Martin, et al.
Published: (2024)

MEME: Multi-entity & Evolving Memory Evaluation
by: Jung, Seokwon, et al.
Published: (2026)

What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
by: Do, Heejin, et al.
Published: (2025)

PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
by: Xiao, Yijia, et al.
Published: (2023)

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

Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation
by: Mohamed, Asim, et al.
Published: (2025)

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
by: Li, Yansong, et al.
Published: (2023)

Parameter-Efficient Fine-Tuning with Differential Privacy for Robust Instruction Adaptation in Large Language Models
by: Huang, Yulin, et al.
Published: (2025)

Fine-Tuning Large Language Models with User-Level Differential Privacy
by: Charles, Zachary, et al.
Published: (2024)

Compressed Context Memory For Online Language Model Interaction
by: Kim, Jang-Hyun, et al.
Published: (2023)

Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models
by: Salemi, Alireza, et al.
Published: (2024)

Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models
by: Flemings, James, et al.
Published: (2024)

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
by: Guan, Zihan, et al.
Published: (2025)

Toward Interactive Regional Understanding in Vision-Large Language Models
by: Lee, Jungbeom, et al.
Published: (2024)

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation
by: Li, Xianzhi, et al.
Published: (2024)

Detecting Voice Phishing with Precision: Fine-Tuning Small Language Models
by: Sim, Ju Yong, et al.
Published: (2025)

Differentially Private Steering for Large Language Model Alignment
by: Goel, Anmol, et al.
Published: (2025)

Privacy-Preserving Instructions for Aligning Large Language Models
by: Yu, Da, et al.
Published: (2024)

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
by: Mireshghallah, Niloofar, et al.
Published: (2023)

Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory
by: Li, Haoran, et al.
Published: (2024)

The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
by: Chen, Xiaoyi, et al.
Published: (2023)

Contextualized Privacy Defense for LLM Agents
by: Wen, Yule, et al.
Published: (2026)

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
by: Fan, Wei, et al.
Published: (2024)

On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models
by: Sun, Qian, et al.
Published: (2024)

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

Playing repeated games with Large Language Models
by: Akata, Elif, et al.
Published: (2023)

Fine-Tuning Medical Language Models for Enhanced Long-Contextual Understanding and Domain Expertise
by: Yang, Qimin, et al.
Published: (2024)

Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainability
by: Chen, Yuxin, et al.
Published: (2025)

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
by: Yi, Biao, et al.
Published: (2025)

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs
by: Sahoo, Subramanyam
Published: (2026)

Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations
by: Wang, Haoran, et al.
Published: (2026)

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
by: Ruan, Zhiwen, et al.
Published: (2026)

QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models
by: Jeon, Hyesung, et al.
Published: (2025)

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
by: Rubinstein, Alexander, et al.
Published: (2025)