Imagen de Portada

Stealix: Model Stealing via Prompt Evolution

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhuang, Zhixiong, Wang, Hui-Po, Nicolae, Maria-Irina, Fritz, Mario
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Stealthy Imitation: Reward-guided Environment-free Policy Stealing
por: Zhuang, Zhixiong, et al.
Publicado: (2024)

ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks
por: Zhuang, Zhixiong, et al.
Publicado: (2025)

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment
por: Shen, Yaling, et al.
Publicado: (2025)

Prompt Stealing Attacks Against Text-to-Image Generation Models
por: Shen, Xinyue, et al.
Publicado: (2023)

On Stealing Graph Neural Network Models
por: Podhajski, Marcin, et al.
Publicado: (2025)

TrEEStealer: Stealing Decision Trees via Enclave Side Channels
por: Sander, Jonas, et al.
Publicado: (2026)

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
por: Feng, Shanglun, et al.
Publicado: (2024)

Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity
por: Zhu, Zhihao, et al.
Publicado: (2023)

Stealing Training Graphs from Graph Neural Networks
por: Lin, Minhua, et al.
Publicado: (2024)

Transpose Attack: Stealing Datasets with Bidirectional Training
por: Amit, Guy, et al.
Publicado: (2023)

DM4Steal: Diffusion Model For Link Stealing Attack On Graph Neural Networks
por: Chen, Jinyin, et al.
Publicado: (2024)

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
por: Lou, Jiadong, et al.
Publicado: (2025)

Stealing User Prompts from Mixture of Experts
por: Yona, Itay, et al.
Publicado: (2024)

Watermark Stealing in Large Language Models
por: Jovanović, Nikola, et al.
Publicado: (2024)

Model-Guardian: Protecting against Data-Free Model Stealing Using Gradient Representations and Deceptive Predictions
por: Yang, Yunfei, et al.
Publicado: (2025)

Link Stealing Attacks Against Inductive Graph Neural Networks
por: Wu, Yixin, et al.
Publicado: (2024)

I Stolenly Swear That I Am Up to (No) Good: Design and Evaluation of Model Stealing Attacks
por: Oliynyk, Daryna, et al.
Publicado: (2025)

Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels
por: Shukla, Shubhi, et al.
Publicado: (2024)

Defending Jailbreak Prompts via In-Context Adversarial Game
por: Zhou, Yujun, et al.
Publicado: (2024)

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
por: Küchler, Nicolas, et al.
Publicado: (2025)

Evaluating Efficacy of Model Stealing Attacks and Defenses on Quantum Neural Networks
por: Kundu, Satwik, et al.
Publicado: (2024)

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
por: Yoon, Do-hyeon, et al.
Publicado: (2025)

How Feasible is Augmenting Fake Nodes with Learnable Features as a Counter-strategy against Link Stealing Attacks?
por: Mostafiz, Mir Imtiaz, et al.
Publicado: (2025)

Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction
por: Wu, Shuchi, et al.
Publicado: (2023)

Examining the Threat Landscape: Foundation Models and Model Stealing
por: Raj, Ankita, et al.
Publicado: (2025)

Large Language Models for Link Stealing Attacks Against Graph Neural Networks
por: Guan, Faqian, et al.
Publicado: (2024)

Exploring Query Efficient Data Generation towards Data-free Model Stealing in Hard Label Setting
por: Pei, Gaozheng, et al.
Publicado: (2024)

Bypassing Prompt Guards in Production with Controlled-Release Prompting
por: Fairoze, Jaiden, et al.
Publicado: (2025)

PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
por: Zou, Wei, et al.
Publicado: (2025)

Prompt Obfuscation for Large Language Models
por: Pape, David, et al.
Publicado: (2024)

DP-SNP-TIHMM: Differentially Private, Time-Inhomogeneous Hidden Markov Models for Synthesizing Genome-Wide Association Datasets
por: Rahimian, Shadi, et al.
Publicado: (2025)

Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
por: Lin, Minhua, et al.
Publicado: (2024)

QuantumLeak: Stealing Quantum Neural Networks from Cloud-based NISQ Machines
por: Fu, Zhenxiao, et al.
Publicado: (2024)

Teach LLMs to Phish: Stealing Private Information from Language Models
por: Panda, Ashwinee, et al.
Publicado: (2024)

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis
por: Kang, Mintong, et al.
Publicado: (2025)

Efficient and Adaptable Detection of Malicious LLM Prompts via Bootstrap Aggregation
por: Hassan, Shayan Ali, et al.
Publicado: (2026)

VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
por: Du, Xuefeng, et al.
Publicado: (2024)

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
por: Garov, Kostadin, et al.
Publicado: (2023)

Death by a Thousand Prompts: Open Model Vulnerability Analysis
por: Chang, Amy, et al.
Publicado: (2025)

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
por: Zhao, Kaixiang, et al.
Publicado: (2026)