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.
Watermarking Graph Neural Networks based on Backdoor Attacks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Roblox's automated chat moderation fails to catch numerous unsafe messages involving grooming, sexualization of minors, bullying, violence, self-harm, and sensitive information sharing, with users evading detection through various techniques.
Benchmarking finds FHE faster than SMPC for regressions and simple dense networks (especially with GPUs), while SMPC performs better on complex CNN models.
citing papers explorer
-
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.
-
An Evaluation of Chat Safety Moderations in Roblox
Roblox's automated chat moderation fails to catch numerous unsafe messages involving grooming, sexualization of minors, bullying, violence, self-harm, and sensitive information sharing, with users evading detection through various techniques.
-
A Pragmatic Comparison of Cryptographic Computation Technologies for Machine Learning
Benchmarking finds FHE faster than SMPC for regressions and simple dense networks (especially with GPUs), while SMPC performs better on complex CNN models.