Dell products l.p. (20240346150). EARLY AND ADAPTIVE STREAM SAMPLING SYSTEM AND METHOD FOR MACHINE LEARNING-BASED OPTIMIZATIONS IN STORAGE SYSTEMS simplified abstract
EARLY AND ADAPTIVE STREAM SAMPLING SYSTEM AND METHOD FOR MACHINE LEARNING-BASED OPTIMIZATIONS IN STORAGE SYSTEMS
Organization Name
Inventor(s)
Shaul Dar of Petach Tikva (IL)
Ramakanth Kanagovi of Telangana (IN)
Guhesh Swaminathan of Chennai (IN)
EARLY AND ADAPTIVE STREAM SAMPLING SYSTEM AND METHOD FOR MACHINE LEARNING-BASED OPTIMIZATIONS IN STORAGE SYSTEMS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240346150 titled 'EARLY AND ADAPTIVE STREAM SAMPLING SYSTEM AND METHOD FOR MACHINE LEARNING-BASED OPTIMIZATIONS IN STORAGE SYSTEMS
The patent application describes techniques for early and adaptive I/O stream sampling in a storage system for ML-based optimizations. By sampling a sub-slice of data from successive operations on a storage object, generating features, processing them using an ML model, and determining a probability score, the system can identify threats.
- Obtaining a sub-slice of sampled data through early sampling of successive operations on a storage object
- Generating features based on the sub-slice and processing them using an ML model
- Determining a probability score based on the ML model's output
- Comparing the probability score to continuous variable distributions for benign and threat classes
- Assigning a "threat" class label if the similarity between class signatures exceeds a predetermined level
Potential Applications: - Enhancing security in storage systems by detecting threats early - Optimizing storage performance based on ML analysis of I/O streams
Problems Solved: - Early detection of threats in storage systems - Adaptive optimization of storage based on ML insights
Benefits: - Improved security measures - Enhanced storage system performance - Efficient threat detection and response
Commercial Applications: Title: "Enhancing Storage Security and Performance with ML-Based Threat Detection" This technology can be applied in industries such as cybersecurity, cloud storage, and data centers to improve threat detection and storage optimization.
Questions about the technology: 1. How does early and adaptive I/O stream sampling improve threat detection in storage systems? 2. What are the key benefits of using ML-based optimizations in storage systems for threat detection?
Original Abstract Submitted
techniques for performing early and adaptive io stream sampling for ml-based optimizations in a storage system. the techniques include obtaining a sub-slice of sampled data by performing early sampling of a slice of successive operations directed to a storage object. the techniques include generating features based on the sub-slice, processing the features using an ml model, and generating a probability score based on the ml model's output. the techniques include determining that the probability score falls within an overlap range of continuous variable distributions for benign and threat classes of data. the techniques include, in response to the probability score exceeding a specified threshold, comparing a class signature of the sub-slice with a target class signature of the threat class of data to determine a similarity between the class signatures, and, in response to the similarity exceeding a predetermined similarity level, assigning a “threat” class label to the probability score.
