Probabilistic swaps combine adaptor signatures with OPRFs to let one party receive an asset with a publicly fixed probability in an atomic, bias-resistant way on Bitcoin and similar chains.
Canonical reference
Model Stealing Attacks Against Inductive Graph Neural Networks
Canonical reference. 83% of citing Pith papers cite this work as background.
5
Pith papers citing it
Background
83% of classified citations
citation-role summary
background 5
extension 1
citation-polarity summary
years
2026 5representative 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.
PINSIGHT shows Wi-Fi PIN code inference attacks generalize across environmental changes but degrade when keystroke signal encoding shifts, meaning current state-of-the-art claims overstate real-world threats.
Adversarial examples enable AI authority laundering by causing production VLMs to give authoritative but wrong responses on subtly perturbed images, with success rates of 22-100% using decade-old attack methods.
citing papers explorer
-
Probabilistic Atomic Swaps for Bitcoin and Friends
Probabilistic swaps combine adaptor signatures with OPRFs to let one party receive an asset with a publicly fixed probability in an atomic, bias-resistant way on Bitcoin and similar chains.
-
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.
-
PINSIGHT: A Comprehensive Threat Exploration of Domain-Adaptive Wi-Fi based PIN Code Inference
PINSIGHT shows Wi-Fi PIN code inference attacks generalize across environmental changes but degrade when keystroke signal encoding shifts, meaning current state-of-the-art claims overstate real-world threats.
-
Laundering AI Authority with Adversarial Examples
Adversarial examples enable AI authority laundering by causing production VLMs to give authoritative but wrong responses on subtly perturbed images, with success rates of 22-100% using decade-old attack methods.
- PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization