Imagen de Portada

Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Guanzhong, Qin, Zhenghan, Yang, Mingxin, Zhou, Yajie, Fan, Tao, Du, Tianyu, Xu, Zenglin
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security K.6.5
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Predicting known Vulnerabilities from Attack News: A Transformer-Based Approach
por: Othman, Refat, et al.
Publicado: (2026)

I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference
por: Gao, Zibo, et al.
Publicado: (2025)

A Relevance Model for Threat-Centric Ranking of Cybersecurity Vulnerabilities
por: McCoy, Corren, et al.
Publicado: (2024)

ADMIn: Attacks on Dataset, Model and Input. A Threat Model for AI Based Software
por: Kumar, Vimal, et al.
Publicado: (2024)

Expanding the Attack Scenarios of SAE J1939: A Comprehensive Analysis of Established and Novel Vulnerabilities in Transport Protocol
por: Lee, Hwejae, et al.
Publicado: (2024)

Enhancing Energy Sector Resilience: Integrating Security by Design Principles
por: Shirtz, Dov, et al.
Publicado: (2024)

Virtualization-based Penetration Testing Study for Detecting Accessibility Abuse Vulnerabilities in Banking Apps in East and Southeast Asia
por: Minn, Wei, et al.
Publicado: (2026)

Non-Linear Trajectory Modeling for Multi-Step Gradient Inversion Attacks in Federated Learning
por: Xia, Li, et al.
Publicado: (2025)

Optimisation of cyber insurance coverage with selection of cost effective security controls
por: Uuganbayar, Ganbayar, et al.
Publicado: (2025)

The Vehicle May Be Sick: Denial of Diagnostic Services by Exploiting the CAN Transport Protocol
por: Baek, Seungjin, et al.
Publicado: (2026)

Rubber Mallet: A Study of High Frequency Localized Bit Flips and Their Impact on Security
por: Adiletta, Andrew, et al.
Publicado: (2025)

Active Authentication via Korean Keystrokes Under Varying LLM Assistance and Cognitive Contexts
por: Roh, Dong Hyun, et al.
Publicado: (2025)

Dynamic Vulnerability Patching for Heterogeneous Embedded Systems Using Stack Frame Reconstruction
por: Zhou, Ming, et al.
Publicado: (2025)

Human Vulnerability Assessment in Cybersecurity: A Systematic Literature Review of Methods, Models, and Instruments
por: Papatsaroucha, Dimitra, et al.
Publicado: (2026)

Spill The Beans: Exploiting CPU Cache Side-Channels to Leak Tokens from Large Language Models
por: Adiletta, Andrew, et al.
Publicado: (2025)

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study
por: Xu, Luyao, et al.
Publicado: (2026)

Benchmarking Large Language Models for IoC Recovery under Adversarial Code Obfuscation and Encryption
por: Morales, Jaime, et al.
Publicado: (2026)

Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships
por: Oh, Myung Gyo, et al.
Publicado: (2024)

RADEP: A Resilient Adaptive Defense Framework Against Model Extraction Attacks
por: Chakraborty, Amit, et al.
Publicado: (2025)

Density-aware Sample-specific Attack
por: Wang, Qiyuan, et al.
Publicado: (2026)

ZTD$_{JAVA}$: Mitigating Software Supply Chain Vulnerabilities via Zero-Trust Dependencies
por: Amusuo, Paschal C., et al.
Publicado: (2023)

Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection
por: Graves, Marcus
Publicado: (2026)

Reference-Free Spectral Analysis of EM Side-Channels for Always-on Hardware Trojan Detection
por: Tahghigh, Mahsa, et al.
Publicado: (2026)

Building Your Own Trusted Execution Environments Using FPGA
por: Armanuzzaman, Md, et al.
Publicado: (2022)

SpyChain: Multi-Vector Supply Chain Attacks on Small Satellite Systems
por: Vanlyssel, Jack, et al.
Publicado: (2025)

Peak + Accumulation: A Proxy-Level Scoring Formula for Multi-Turn LLM Attack Detection
por: Corll, J Alex
Publicado: (2026)

Measuring Harmfulness of Computer-Using Agents
por: Tian, Aaron Xuxiang, et al.
Publicado: (2025)

Towards Zero Trust Architecture: A Pilot Study on Information Systems Security Readiness amongst Small and Medium Enterprises
por: Deng, Yu, et al.
Publicado: (2026)

Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs
por: Mosievskiy, Nikita
Publicado: (2026)

Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling
por: Alboushy, Badr, et al.
Publicado: (2026)

ARMOUR US: Android Runtime Zero-permission Sensor Usage Monitoring from User Space
por: Long, Yan, et al.
Publicado: (2025)

RealVuln: Benchmarking Rule-Based, General-Purpose LLM, and Security-Specialized Scanners on Real-World Code
por: Pellew, John, et al.
Publicado: (2026)

MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization
por: Gu, Yongtong, et al.
Publicado: (2026)

Memory Forensics Techniques for Automated Detection and Analysis of Go Malware
por: Ali, Hala, et al.
Publicado: (2026)

The Discovery, Disclosure, and Investigation of CVE-2024-25825
por: Chasens, Hunter
Publicado: (2025)

Post-quantum Federated Learning: Secure And Scalable Threat Intelligence For Collaborative Cyber Defense
por: Nayak, Prabhudarshi, et al.
Publicado: (2026)

Silent Consent, Persistent Risk: Android Permission Groups and Custom Permissions
por: Akanji, Olawale Amos, et al.
Publicado: (2026)

Enabling Practical and Privacy-Preserving Image Processing
por: Wang, Chao, et al.
Publicado: (2024)

LLM Scalability Risk for Agentic-AI and Model Supply Chain Security
por: Ahi, Kiarash, et al.
Publicado: (2026)

vCause: Efficient and Verifiable Causality Analysis for Cloud-based Endpoint Auditing
por: Song, Qiyang, et al.
Publicado: (2026)