Cover Image

CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Arachchige, Shashie Dilhara Batan, Zhao, Benjamin Zi Hao, Asghar, Hassan Jameel, Vatsalan, Dinusha, Kaafar, Dali
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Protecting User Prompts Via Character-Level Differential Privacy
by: Arachchige, Shashie Dilhara Batan, et al.
Published: (2026)

$d_X$-Privacy for Text and the Curse of Dimensionality
by: Asghar, Hassan Jameel, et al.
Published: (2024)

Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions
by: Carpentier, Robin, et al.
Published: (2024)

Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption
by: Asghar, Hassan Jameel, et al.
Published: (2023)

Property-Preserving Hashing for $\ell_1$-Distance Predicates: Applications to Countering Adversarial Input Attacks
by: Asghar, Hassan, et al.
Published: (2025)

A Large-Scale Empirical Analysis of Custom GPTs' Vulnerabilities in the OpenAI Ecosystem
by: Ogundoyin, Sunday Oyinlola, et al.
Published: (2025)

Integrating PETs into Software Applications: A Game-Based Learning Approach
by: Boteju, Maisha, et al.
Published: (2024)

Efficient Verifiable Differential Privacy with Input Authenticity in the Local and Shuffle Model
by: Bontekoe, Tariq, et al.
Published: (2024)

On the Robustness of Malware Detectors to Adversarial Samples
by: Salman, Muhammad, et al.
Published: (2024)

Answering Counting Queries with Differential Privacy on a Quantum Computer
by: Mukherjee, Arghya, et al.
Published: (2026)

Efficient Fault-Tolerant Quantum Protocol for Differential Privacy in the Shuffle Model
by: Asghar, Hassan Jameel, et al.
Published: (2024)

Privacy-Preserving IoT in Connected Aircraft Cabin
by: Vyas, Nilesh, et al.
Published: (2025)

Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
by: Xie, Jingyuan, et al.
Published: (2026)

When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning
by: Zhu, Sichen, et al.
Published: (2025)

SpaLLM-Guard: Pairing SMS Spam Detection Using Open-source and Commercial LLMs
by: Salman, Muhammad, et al.
Published: (2025)

Unveiling Privacy and Security Gaps in Female Health Apps
by: Hassan, Muhammad, et al.
Published: (2025)

Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models
by: Zhang, Boyang, et al.
Published: (2025)

A Framework for Managing Multifaceted Privacy Leakage While Optimizing Utility in Continuous LBS Interactions
by: Bkakria, Anis, et al.
Published: (2024)

FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning
by: Zhang, Zhuo, et al.
Published: (2024)

Computing Maximal Per-Record Leakage and Leakage-Distortion Functions for Privacy Mechanisms under Entropy-Constrained Adversaries
by: Wu, Genqiang, et al.
Published: (2026)

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
by: Hughes, Anthony, et al.
Published: (2025)

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
by: Tang, Xinyu, et al.
Published: (2023)

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

Driving Privacy Forward: Mitigating Information Leakage within Smart Vehicles through Synthetic Data Generation
by: Parikh, Krish
Published: (2024)

CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
by: Wang, Weiqi, et al.
Published: (2025)

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
by: Ganev, Georgi, et al.
Published: (2025)

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
by: Yoon, Sangyeon, et al.
Published: (2026)

Zebrafix: Mitigating Memory-Centric Side-Channel Leakage via Interleaving
by: Pätschke, Anna, et al.
Published: (2025)

POLARIS: Explainable Artificial Intelligence for Mitigating Power Side-Channel Leakage
by: Mahfuz, Tanzim, et al.
Published: (2025)

The Hidden Costs of Domain Fine-Tuning: Pii-Bearing Data Degrades Safety and Increases Leakage
by: Choudhari, Jayesh, et al.
Published: (2026)

PrivTru: A Privacy-by-Design Data Trustee Minimizing Information Leakage
by: Gehring, Lukas, et al.
Published: (2025)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
by: Fu, Jie, et al.
Published: (2026)

Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
by: Huang, Tao, et al.
Published: (2026)

A Classification-by-Retrieval Framework for Few-Shot Anomaly Detection to Detect API Injection Attacks
by: Aharon, Udi, et al.
Published: (2024)

The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
by: Jayawardana, Sandaru, et al.
Published: (2025)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
by: Meng, Jiayang, et al.
Published: (2025)

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
by: Roh, Jaechul, et al.
Published: (2026)

Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detection
by: Trad, Fouad, et al.
Published: (2025)

Quantifying Privacy Leakage in Split Inference via Fisher-Approximated Shannon Information Analysis
by: Deng, Ruijun, et al.
Published: (2025)

Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
by: Allouah, Youssef, et al.
Published: (2024)