Abstract: Methods and systems are described herein for recommending network processing routes when conducting blockchain operations. For example, the system may receive a first user request to perform a first blockchain operation across one or more computer networks to access a first blockchain asset. The system may then determine a first processing characteristic for the first user request and a first plurality of locations of the first blockchain asset (e.g., across the one or more computer networks). The system may then determine a first plurality of network routes to a first subset of the first plurality of locations. The system may then filter the first plurality of network routes (e.g., based on the first processing characteristic) to generate a first subset of the plurality of network routes. Based on the first subset of the plurality of network routes, the system may generate a first recommendation for performing the blockchain operation.

Abstract: A system that deploys a first smart contract that include a set of predefined functions that enable exchange of a first cryptocurrency on a first blockchain network. Additionally, the system deploys a second smart contract with the set of predefined functions that enable exchange of a second cryptocurrency on a second blockchain network. Furthermore, the two sets of smart contracts allow for the blockchain operations to be conducted by referencing an exchange platform supported by the system. By referencing the exchange platform, the corresponding sets of functions may be activated to perform exchanges across the blockchain networks.

Abstract: In some embodiments, in connection with an API request to transact with an entity, a first conversion rate associated with a first time may be determined, where the first conversion rate is a current conversion rate for an on-chain asset at the first time; Based on a monitoring of a blockchain, a receipt of the on-chain asset at a second blockchain address from a first blockchain address associated with the user may be detected on the blockchain. In response to the detection, the on-chain asset may be converted to an off-chain asset at a second time associated with a second conversion rate, the second conversion rate being the current conversion rate for the on-chain asset at the second time. An amount of the off-chain asset may be transmitted to the entity, where the amount of the off-chain asset sent to the entity is based on the first conversion rate.

Abstract: Methods and systems use a second dataset comprising independently validated data based on labeled blockchain operations previously processed through the blockchain network. The use of the second dataset in conjunction with the dataset comprising labeled blockchain characteristics data received from a plurality of sources provides a comprehensive input for a machine learning model to identify and label suspicious blockchain operations. By doing so, the system mitigates fraudulent, criminal, or suspicious transactions. For example, the system may send an alert to a user if a behavior type is deemed a high risk by the machine learning model; the system may furthermore hold the funds associated with the blockchain operation in a separate account while the transaction is manually reviewed.

Abstract: In certain embodiments, model unlearning verifiability may be facilitated. In some embodiments, in connection with a request for unlearning of a dataset for a machine learning model, an unlearning process may be performed on the machine learning model, where the unlearning process involves multiple stages, for the unlearning of the dataset, at which model instances of the machine learning model are respectively generated. One or more proofs or hash-based values corresponding to the model instances may be generated, such as first and second hash-based values corresponding to first and second model instances of the machine learning model generated at first and second stages of the unlearning process, respectively (e.g., where the second stage depends on the first stage). The proofs or hash-based values may then be stored at one or more database locations of a database to enable verification of the performance of the unlearning process.

Abstract: Methods and systems are described herein for performing a cold start operation of a system for acquiring non-fungible tokens (NFTs) using on-chain data. In particular, a user feed initialization system may receive an on-chain address associated with a cryptography-based storage application (e.g., an address associated with a crypto wallet of a user) and determine, based on the on-chain address, NFTs that the user's cryptography-based storage application controls (e.g., NFTs that the user owns). The user feed initialization system may use on-chain data associated with the NFTs (e.g., via interrogating the on-chain programs associated with the NFTs that the user owns) to identify (e.g., via a machine learning model) other NFTs that the user may desire to acquire.

Abstract: Methods and systems for a processing architecture that maintains a separate logic pathway corresponding to a first operation type and a second operation type, until a blockchain operation is submitted to the blockchain network using either the first operation type or a second operation type. Following submission of the blockchain operation to the blockchain network, the architecture collapses the parallel logic pathways to a single logical pathway for both types.

Abstract: Methods and systems for parsing and identifying unindexed parameters and other information (e.g., a token contract address) that may appear encoded in event data. Specifically, the system may retrieve bytecode for an identified blockchain operation (e.g., a transaction). The system may then segregate the bytecode into constructor arguments, code sections, and/or metadata. The system may then parse the segregated portions of bytecode for bytecode representations that are based on function signatures, event signatures, token standards, and/or contract addresses. In some embodiments, the system may further narrow the pool of known bytecode representations that are compared against the remaining sections of bytecode based on bytecode representations corresponding to a particular type of blockchain network standard.

Abstract: In certain embodiments, model unlearning verifiability may be facilitated. In some embodiments, in connection with a request for unlearning of a dataset for a machine learning model, an unlearning process may be performed on the machine learning model, where the unlearning process involves multiple stages, for the unlearning of the dataset, at which model instances of the machine learning model are respectively generated. One or more proofs or hash-based values corresponding to the model instances may be generated, such as first and second hash-based values corresponding to first and second model instances of the machine learning model generated at first and second stages of the unlearning process, respectively (e.g., where the second stage depends on the first stage). The proofs or hash-based values may then be stored at one or more database locations of a database to enable verification of the performance of the unlearning process.

Abstract: Methods and system for managing partial private keys for cryptography-based, storage applications used in blockchain operations and/or facilitating secure authentication when conducting blockchain operations using cryptography-based, storage applications. For example, the methods and system may perform a plurality of blockchain operations for digital assets stored in a first cryptography-based, storage application, wherein the first cryptography-based, storage application corresponds to a first partial private key, and wherein the first partial private key is stored on a first user device, and wherein the second partial private key is not accessible to platform service facilitating the first cryptography-based, storage application.

Abstract: Methods and systems are described herein for performing cryptographic operations. In particular, the system receives identifiers for blockchain operation requests (e.g., bids) for transferring control of a non-fungible token (NFT) from a first blockchain address to a second blockchain address in exchange for payment (e.g., fungible tokens). The system provides visual indications of the blockchain operation requests to a first user device associated with a first cryptography-based storage application (e.g., an address associated with a cryptographic wallet of a user). The system may receive, from the first user device, a command to approve one of the blockchain operation requests and may determine an on-chain program (e.g., smart contract) for transferring the NFT. The system may submit, to the on-chain program, a request to transfer the NFT to the second blockchain address associated with the approved first blockchain operation request.

Abstract: Methods and systems are described herein for performing privacy-preserving operation of a system for acquiring non-fungible tokens (NFTs) using on-chain data. In particular, a user feed initialization system may determine that a privacy-preserving login is requested and may receive an on-chain address associated with a cryptography-based storage application (e.g., an address associated with a crypto wallet of a user) and determine, based on the on-chain address, NFTs that the user's cryptography-based storage application controls (e.g., NFTs that the user owns). The user feed initialization system may use on-chain data associated with the NFTs (e.g., via interrogating the on-chain programs associated with the NFTs that the user owns) to identify (e.g., via a machine learning model) other NFTs that the user may desire to acquire.