SDS extracts stable spectral signatures from diffusion model denoisers via frequency-controlled perturbations, achieving 99.9% attribution accuracy across eight models and 96.2% under prompt shift.
Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
COPYCOP identifies copycat GNNs by matching their node embeddings despite architectural differences and adversarial transformations, backed by theoretical guarantees and tests on 14 datasets across 5 architectures.
GaussLock embeds traps targeting position, scale, rotation, opacity, and color in 3D Gaussian models to degrade unauthorized fine-tunes while preserving authorized performance.
Landseer offers a containerized modular system to integrate and evaluate combinations of machine learning defenses, with an initial analysis of 35 defenses highlighting replicability challenges.
SIF creates semantically in-distribution fingerprints for LVLMs by distilling text watermarks into visual inputs and optimizing for robustness against detection and modification.
citing papers explorer
-
Diffusion Model Attribution via Spectral Coupling of Denoiser Responses
SDS extracts stable spectral signatures from diffusion model denoisers via frequency-controlled perturbations, achieving 99.9% attribution accuracy across eight models and 96.2% under prompt shift.
-
COPYCOP: Ownership Verification for Graph Neural Networks
COPYCOP identifies copycat GNNs by matching their node embeddings despite architectural differences and adversarial transformations, backed by theoretical guarantees and tests on 14 datasets across 5 architectures.
-
Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
GaussLock embeds traps targeting position, scale, rotation, opacity, and color in 3D Gaussian models to degrade unauthorized fine-tunes while preserving authorized performance.
-
Landseer: Exploring the Machine Learning Defense Landscape
Landseer offers a containerized modular system to integrate and evaluate combinations of machine learning defenses, with an initial analysis of 35 defenses highlighting replicability challenges.
-
SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models
SIF creates semantically in-distribution fingerprints for LVLMs by distilling text watermarks into visual inputs and optimizing for robustness against detection and modification.