Imagen de Portada

PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Ruixuan, Wang, Tianhao, Cao, Yang, Xiong, Li
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run
por: Liu, Ruixuan, et al.
Publicado: (2025)

ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
por: Liu, Ruixuan, et al.
Publicado: (2024)

Enhancing Pre-Trained Language Models for Vulnerability Detection via Semantic-Preserving Data Augmentation
por: Qi, Weiliang, et al.
Publicado: (2024)

Revisiting Privacy-Utility Trade-off for DP Training with Pre-existing Knowledge
por: Zheng, Yu, et al.
Publicado: (2024)

Benchmarking Secure Sampling Protocols for Differential Privacy
por: Fu, Yucheng, et al.
Publicado: (2024)

SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
por: Xia, Yuyang, et al.
Publicado: (2025)

How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?
por: Liu, Meiqi, et al.
Publicado: (2025)

VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
por: Kong, Cong, et al.
Publicado: (2026)

Network-Aware Differential Privacy
por: Li, Zhou, et al.
Publicado: (2025)

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
por: Zhao, Tianhang, et al.
Publicado: (2025)

FedSGT: Exact Federated Unlearning via Sequential Group-based Training
por: Zhang, Bokang, et al.
Publicado: (2025)

Machine Unlearning of Pre-trained Large Language Models
por: Yao, Jin, et al.
Publicado: (2024)

Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run
por: Xiang, Zihang, et al.
Publicado: (2025)

Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
por: Bouaziz, Wassim, et al.
Publicado: (2025)

Language of Network: A Generative Pre-trained Model for Encrypted Traffic Comprehension
por: Zhao, Di, et al.
Publicado: (2025)

APT-CGLP: Advanced Persistent Threat Hunting via Contrastive Graph-Language Pre-Training
por: Qiu, Xuebo, et al.
Publicado: (2025)

Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning
por: Lee, Hong kyu, et al.
Publicado: (2025)

Tight Privacy Audit in One Run
por: Xiang, Zihang, et al.
Publicado: (2025)

Enhanced Privacy Bound for Shuffle Model with Personalized Privacy
por: Liu, Yixuan, et al.
Publicado: (2024)

PrePaMS: Privacy-Preserving Participant Management System for Studies with Rewards and Prerequisites
por: Meißner, Echo, et al.
Publicado: (2024)

Detecting Malicious Intents in Smart Contracts with Pre-trained Programming Language Models
por: Huang, Youwei, et al.
Publicado: (2025)

The Security and Privacy of Mobile Edge Computing: An Artificial Intelligence Perspective
por: Wang, Cheng, et al.
Publicado: (2024)

Persistent Pre-Training Poisoning of LLMs
por: Zhang, Yiming, et al.
Publicado: (2024)

Always be Pre-Training: Representation Learning for Network Intrusion Detection with GNNs
por: Gu, Zhengyao, et al.
Publicado: (2024)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
por: Wen, Yuxin, et al.
Publicado: (2024)

Transfer Learning in Pre-Trained Large Language Models for Malware Detection Based on System Calls
por: Sánchez, Pedro Miguel Sánchez, et al.
Publicado: (2024)

PrivCode: When Code Generation Meets Differential Privacy
por: Liu, Zheng, et al.
Publicado: (2025)

Private Means and the Curious Incident of the Free Lunch
por: Fitzsimons, Jack, et al.
Publicado: (2024)

Preserving Node-level Privacy in Graph Neural Networks
por: Xiang, Zihang, et al.
Publicado: (2023)

UOR: Universal Backdoor Attacks on Pre-trained Language Models
por: Du, Wei, et al.
Publicado: (2023)

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models
por: Ding, Zikang, et al.
Publicado: (2026)

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
por: He, Yu, et al.
Publicado: (2025)

Provable Privacy with Non-Private Pre-Processing
por: Hu, Yaxi, et al.
Publicado: (2024)

Augmenting Parameter-Efficient Pre-trained Language Models with Large Language Models
por: Anand, Saurabh, et al.
Publicado: (2026)

PLLM-CS: Pre-trained Large Language Model (LLM) for Cyber Threat Detection in Satellite Networks
por: Hassanin, Mohammed, et al.
Publicado: (2024)

Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
por: Pang, Yan, et al.
Publicado: (2023)

MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector
por: Fu, Wenjie, et al.
Publicado: (2024)

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
por: Kong, Cong, et al.
Publicado: (2024)

HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense
por: Li, Siyuan, et al.
Publicado: (2026)

ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction
por: Zhou, Tong, et al.
Publicado: (2025)