Random Address Generation for Nonvolatile Memory Security
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional linear access methods for sensitive data in nonvolatile memory (NVM) simplify invasive attacks by allowing adversaries to infer secret data through monitoring data signals, as the number of data lines is typically smaller than address lines, making it easier for attackers to recover the data.
Innovation Solution
A random number generator is used to generate access patterns for addresses, and a scoreboard bank of registers tracks used addresses, ensuring that each address is output only once within a set or range, preventing adversaries from piecing together the secret data by accessing it in random order while maintaining minimum access time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If linear access methods are used for sensitive data in nonvolatile memory, then the access process is simple and fast, but adversaries can easily infer secret data by monitoring data signals
Solution Approach 1:
The patent applies dynamics by transforming the static linear access pattern into a dynamic random access pattern. The address generation logic dynamically selects addresses using a random number generator, making the access pattern unpredictable and changing with each access operation, thereby preventing adversaries from inferring secret data through monitoring
Solution Approach 2:
The patent introduces an intermediary component (address generation logic with random number generator) between the data storage and the access process. This intermediary randomizes the address selection, decoupling the physical storage location from the logical access sequence, thereby protecting the secret data from direct inference through data signal monitoring
2Object-affected harmful factors
If random access patterns are used to prevent adversaries from retrieving sensitive data, then security is enhanced, but access time may increase
Solution Approach 1:
The patent applies preliminary action by pre-generating and storing a mapping between linear addresses and random addresses in a lookup table before actual data access occurs. This pre-computation enables the system to quickly translate linear access requests into randomized physical addresses without adding significant overhead during the actual data retrieval process
Solution Approach 2:
The patent changes the parameter of address selection from deterministic (linear sequence) to probabilistic (random selection). By modifying the address generation mechanism to use random number generation, the system achieves both security enhancement and maintained access performance through efficient random address mapping
Data Source
AI summary
A random number generator selects addresses while a ‘scoreboard’ bank of registers (or bits) tracks which addresses have already been output (e.g., for storing or retrieval of a portion of the data.) When the scoreboard detects an address has already been output, a second address which has not been used yet is output rather than the randomly selected one. The second address may be selected from nearby addresses that have not already been output.