Imagen de Portada

Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Carlini, Nicholas, Chávez-Saab, Jorge, Hambitzer, Anna, Rodríguez-Henríquez, Francisco, Shamir, Adi
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
por: Ito, Akira, et al.
Publicado: (2025)

Hard-Label Cryptanalytic Extraction of Neural Network Models
por: Chen, Yi, et al.
Publicado: (2024)

Delving into Cryptanalytic Extraction of PReLU Neural Networks
por: Chen, Yi, et al.
Publicado: (2025)

A Divide-and-Conquer Strategy for Hard-Label Extraction of Deep Neural Networks via Side-Channel Attacks
por: Coqueret, Benoit, et al.
Publicado: (2024)

Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
por: Kurian, Ashley, et al.
Publicado: (2025)

Detecting Adversarial Fine-tuning with Auditing Agents
por: Egler, Sarah, et al.
Publicado: (2025)

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

Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons
por: Zehavi, Irad, et al.
Publicado: (2023)

Eclectic Rule Extraction for Explainability of Deep Neural Network based Intrusion Detection Systems
por: Ables, Jesse, et al.
Publicado: (2024)

Remote Timing Attacks on Efficient Language Model Inference
por: Carlini, Nicholas, et al.
Publicado: (2024)

Fault Injection and Safe-Error Attack for Extraction of Embedded Neural Network Models
por: Hector, Kevin, et al.
Publicado: (2023)

Non-Adaptive Cryptanalytic Time-Space Lower Bounds via a Shearer-like Inequality for Permutations
por: Dinur, Itai, et al.
Publicado: (2025)

Membership Privacy Evaluation in Deep Spiking Neural Networks
por: Li, Jiaxin, et al.
Publicado: (2024)

Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabre
por: Carlini, Nicholas
Publicado: (2024)

Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
por: Torpmann-Hagen, Birk, et al.
Publicado: (2025)

Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach
por: Yang, Guang, et al.
Publicado: (2026)

CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks
por: Wu, Yinghao, et al.
Publicado: (2025)

Analysis and prevention of AI-based phishing email attacks
por: Eze, Chibuike Samuel, et al.
Publicado: (2024)

Protecting Deep Neural Network Intellectual Property with Chaos-Based White-Box Watermarking
por: B, Sangeeth, et al.
Publicado: (2025)

DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
por: Velčický, Patrik, et al.
Publicado: (2024)

Navigating the Deep: End-to-End Extraction on Deep Neural Networks
por: Liu, Haolin, et al.
Publicado: (2025)

Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challenges
por: Sayyed, Sazzad, et al.
Publicado: (2024)

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
por: Xu, Yixiao, et al.
Publicado: (2025)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
por: Carlini, Nicholas, et al.
Publicado: (2025)

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

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

LLMs unlock new paths to monetizing exploits
por: Carlini, Nicholas, et al.
Publicado: (2025)

MALT Powers Up Adversarial Attacks
por: Melamed, Odelia, et al.
Publicado: (2024)

On Evaluating the Durability of Safeguards for Open-Weight LLMs
por: Qi, Xiangyu, et al.
Publicado: (2024)

Defeating Prompt Injections by Design
por: Debenedetti, Edoardo, et al.
Publicado: (2025)

Large-scale online deanonymization with LLMs
por: Lermen, Simon, et al.
Publicado: (2026)

EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
por: Zhou, Ranyang, et al.
Publicado: (2025)

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
por: Hong, Sanghyun, et al.
Publicado: (2024)

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

Towards Anonymous Neural Network Inference
por: Peiyuan, Liao
Publicado: (2025)

Probabilistically Robust Watermarking of Neural Networks
por: Pautov, Mikhail, et al.
Publicado: (2024)

Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates
por: Tsao, Wen-Kwang, et al.
Publicado: (2025)

Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
por: Hönig, Robert, et al.
Publicado: (2024)

Interpret the Predictions of Deep Networks via Re-Label Distillation
por: Hua, Yingying, et al.
Publicado: (2024)

Neural Network Training on Encrypted Data with TFHE
por: Montero, Luis, et al.
Publicado: (2024)