Imagen de Portada

Beyond Slow Signs in High-fidelity Model Extraction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Foerster, Hanna, Mullins, Robert, Shumailov, Ilia, Hayes, Jamie
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
por: Foerster, Hanna, et al.
Publicado: (2025)

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
por: Foerster, Hanna, et al.
Publicado: (2026)

Locking Machine Learning Models into Hardware
por: Clifford, Eleanor, et al.
Publicado: (2024)

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

Interpreting the Repeated Token Phenomenon in Large Language Models
por: Yona, Itay, et al.
Publicado: (2025)

Buffer Overflow in Mixture of Experts
por: Hayes, Jamie, et al.
Publicado: (2024)

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
por: Chaudhari, Harsh, et al.
Publicado: (2026)

Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks
por: Dahiya, Pranav, et al.
Publicado: (2023)

Architectural Neural Backdoors from First Principles
por: Langford, Harry, et al.
Publicado: (2024)

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

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
por: Vero, Mark, et al.
Publicado: (2026)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
por: Thudi, Anvith, et al.
Publicado: (2023)

ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
por: Clifford, Eleanor, et al.
Publicado: (2022)

Watermarking Needs Input Repetition Masking
por: Khachaturov, David, et al.
Publicado: (2025)

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
por: Hayes, Jamie, et al.
Publicado: (2024)

Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography
por: Shumailov, Ilia, et al.
Publicado: (2025)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
por: Shumailov, Ilia, et al.
Publicado: (2024)

Cascading Adversarial Bias from Injection to Distillation in Language Models
por: Chaudhari, Harsh, et al.
Publicado: (2025)

Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness
por: Khachaturov, David, et al.
Publicado: (2024)

Soft Instruction De-escalation Defense
por: Walter, Nils Philipp, et al.
Publicado: (2025)

PHANTOM: Progressive High-fidelity Adversarial Network for Threat Object Modeling
por: Al-Karaki, Jamal, et al.
Publicado: (2025)

Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
por: Kaissis, Georgios, et al.
Publicado: (2024)

Exploring the limits of strong membership inference attacks on large language models
por: Hayes, Jamie, et al.
Publicado: (2025)

Beyond Labeling Oracles: What does it mean to steal ML models?
por: Shafran, Avital, et al.
Publicado: (2023)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
por: Gao, Yue, et al.
Publicado: (2023)

Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning
por: Rinberg, Roy, et al.
Publicado: (2025)

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

Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
por: Gomez, Juan Felipe, et al.
Publicado: (2025)

PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
por: Ertan, Murat Bilgehan, et al.
Publicado: (2026)

The Curse of Recursion: Training on Generated Data Makes Models Forget
por: Shumailov, Ilia, et al.
Publicado: (2023)

A Survey on Model Extraction Attacks and Defenses for Large Language Models
por: Zhao, Kaixiang, et al.
Publicado: (2025)

ceLLMate: Sandboxing Browser AI Agents
por: Meng, Luoxi, et al.
Publicado: (2025)

A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments
por: Zhao, Kaixiang, et al.
Publicado: (2025)

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives
por: Zhao, Kaixiang, et al.
Publicado: (2025)

Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models
por: Wang, Jeffrey G., et al.
Publicado: (2024)

Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices
por: Lee, Younghan, et al.
Publicado: (2024)

VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
por: Yu, Simon, et al.
Publicado: (2025)

Beyond Data Privacy: New Privacy Risks for Large Language Models
por: Du, Yuntao, et al.
Publicado: (2025)

Decentralized Weather Forecasting via Distributed Machine Learning and Blockchain-Based Model Validation
por: Umar, Rilwan, et al.
Publicado: (2025)

Machine Learning Models Have a Supply Chain Problem
por: Meiklejohn, Sarah, et al.
Publicado: (2025)