|
Distributed storage in wireless mesh networks
Navy SBIR 2012.1 - Topic N121-003 MARCOR - Mr. Paul Lambert - [email protected] Opens: December 12, 2011 - Closes: January 11, 2012 N121-003 TITLE: Distributed storage in wireless mesh networks TECHNOLOGY AREAS: Information Systems, Sensors, Electronics, Battlespace ACQUISITION PROGRAM: Marine Air Ground Task Force Command and Control Systems RESTRICTION ON PERFORMANCE BY FOREIGN CITIZENS (i.e., those holding non-U.S. Passports): This topic is "ITAR Restricted". The information and materials provided pursuant to or resulting from this topic are restricted under the International Traffic in Arms Regulations (ITAR), 22 CFR Parts 120 - 130, which control the export of defense-related material and services, including the export of sensitive technical data. Foreign Citizens may perform work under an award resulting from this topic only if they hold the "Permanent Resident Card", or are designated as "Protected Individuals" as defined by 8 U.S.C. 1324b(a)(3). If a proposal for this topic contains participation by a foreign citizen who is not in one of the above two categories, the proposal will be rejected. OBJECTIVE: MAGTF C2 Systems is interested in indentifying a sound technical solution to facilitate distributed storage in wireless mesh networks. The developed protocol should provide an alternative solution for solving the data-at-rest problem. Ultimately, the desired goal is to alleviate sole dependency on encryption. DESCRIPTION: Distributed storage is an important paradigm that has been embraced in many computing contexts, but faces unique challenges in the military austere wireless domain. For instance, the operational domain may dictate that a single data object should be spread across multiple devices for: i) performance; ii) security; and iii) resilience. Meeting the required objectives may require understanding of the physical space in which devices are operating (as opposed to fixed infrastructure), using distribution strategies that prevent insecure reconstitution of objects, etc. There are a couple distributed storage technologies available today, however, each lacks at least one specific property of interest. For example, distributed storage properties include: 1) encryption, 2) erasure coding, 3) complete replication, 4) pre-shared key, 5) relies on external authentication, 6) scales to large sizes, or 7) external infrastructure dependencies. The current solutions include Mobile Distributed File System (MDFS) � containing the properties 1, 2 & 5; Tahoe-LAFS � containing the properties 1, 2, 4, & 7; Unisys Stealth � containing the properties 1, 2, 4, & 7; and GFS & Bigtable � containing the properties 3, 5, 6, & 7. This topic is interested in properties that facilitate distributing the storage without being vulnerable to single points of failure. For example, if one node is lost or compromised, the data is not recoverable without other nodes. Additionally this topic is interested in scaling the protocol, not relying on external infrastructure, not relying on pre-shared keys, or complete replication. An innovative approach of interest is to integrate advanced concepts include erasure coding, Shamir�s threshold based secret sharing algorithm, and symmetric AES cryptography. The resulting system supports two important properties: (1) data can be recovered only if some minimum number of devices are accessible, and (2) sensitive data remains protected even after a small number of devices are compromised. This topic is interested in optimizing mesh networks by leveraging the shared storage capacity and limiting the vulnerability associated with one node inherently hosting the data. PHASE I: This would consist of a feasibility assessment using the proposed distributed storage protocol to meet MC2S program requirements. This phase may be extended beyond developing the proposed solution to prototype in follow-on phases. PHASE II: This phase would consist of prototyping a design meant to meet the requirements of MC2S program, ensuring manufacturability, producibility and reproducibility. This phase would also look at the integrity and maintainability of design, as compared to conventional methods. PHASE III: This phase would consist of perfecting the design, and acquisition of the final solution utilizing government funds (NON-SBIR) under the MC2S program. PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: Ultimately the solution could provide a mechanism to increase storage capacity and reduce security vulnerabilities inherent to mobile devices. REFERENCES: 2. Z. O�Whielacronx. (2011) zfec 1.4.22 erasure codec. [Online]. Available: 3. Tahoe-LAFS. (2010) Tahoe least authority file system. [Online]. Available: 4. A. Dimakis, P. Godfrey, Y. Wu, M. Wainwright, and K. Ramchandran, "Network coding for distributed storage systems," IEEE Transactions on Information Theory, vol. 56, pp. 4539 � 4551, Sep. 2010. 5. Huchton, Scott. "Secure Mobile Distributed File System (MDFS). Naval Postgraduate School. March 2011 KEYWORDS: Distributed File System; Distributed Storage; Bigtable; Unisys Stealth; Google File Storage; Tahoe-LAFS
|