Capability security for transparent distributed object systems

Abstract

A system providing capability security for distributed object systems is disclosed. The basic tenet of capability security is that the right to do something to an object (e.g., invoke a particular object's methods) is represented solely by the holding of a reference to that object. In each of the preferred embodiments described herein, an object is presumed to hold legitimately a reference to a particular object only if the object knows some unpublicized (except under the conditions required by capability security) key associated with the particular object. That is, an object's key is required along with the object's reference. So that capability security is preserved when object references are passed between objects in different processes, the object references being passed are encrypted upon transmission and then decrypted upon arrival at their intended destination. This cryptography can be performed by objects or processes using a variety of techniques, including Diffie-Helman or public/private key cryptography. The cryptography performed in the various embodiments ensures that only the intended recipient of the message can decode the object reference and that a misbehaving object cannot convince another object that it possesses a capability it does not have. Some of the disclosed embodiments provide capability security for transparent distributed object systems, wherein a pair of matched transports handle and encrypt inter-process communications between objects in their respective processes.