International Computers Limited

Fujitsu Services Limited

Thomas Anthony Parker

Robin Denis Arthan

Alexander James Robinson

A system involving a central computer ( ) and a remote computer ( ), which can communicate over a link ( ), is migrated from in-clear working to encrypted working automatically as the computers receive and install long term keys necessary for encrypted communication. When migration is required, the settings at both ends of the link need to be changed to &ldquo;encrypt&rdquo; simultaneously and, particularly, if there are numerous remote computers and the possibility of connection of a remote computer to different central computers, as is possible in virtual private network (VPN) scenarios, severe problems can ensue. Hence, as well as the normal two modes of working &ldquo;in-clear&rdquo; and &ldquo;encrypt&rdquo;, a third mode in which &ldquo;initiate encryption&rdquo; is set at one end of the link and &ldquo;accept encryption&rdquo; is set at the other end of the link is proposed. This third mode ensures that working in-clear can continue over a particular link, such as between a particular VPN server and a particular gateway PC, until a long term key required for encrypted working is installed at both ends of the link, but that once key installation is complete, only encrypted working is possible over that link.

Migration from in-clear to encrypted working over a communications link

Business data flows from one computer system ( ) to another ( ) and its integrity can be protected by cryptographic means, such as digital signatures. In particular, a source system ( ) may use a private key (DSPR) to sign outgoing data, and a destination system ( ) may use a public key (DSPU) to verify incoming data. For security purposes all keys should be changed at scheduled times calculated using factors including key lifetime (from which is calculated the key expiry time) and key delivery time. If a key is compromised it needs to be changed at other than the scheduled time, and in general this will result in calculation of a new scheduled key change time. If a DSPR key is delivered to the source system ( ) encrypted by a key encryption key (KEK), then change to the KEK key will in general also be needed upon compromise of the DSPR key. A new key changetime calculation can be avoided if another public key/private key pair is pre-generated and the public key part pre-supplied to the destination system ( ), where it is stored as a spare. When the existing private key (DSPR) is compromised, the new private key corresponding to the spare is supplied to the source system ( ) and can be put into use immediately. In this case the expiry time of the spare public key will be substantially the same as that of the original public key, as it will deemed to have been in use as of delivery, and recalculation of the key changetime will not be required. Preferably a public key in use at the destination system ( ) is not revoked immediately upon compromise of the corresponding private key, in order to enable messages signed by that private key to be verified at the destination system, using the corresponding public key, during a predetermined time interval (message latency) after signing. A maximum value for the message latency may be set and used as another factor in the scheduled key change time calculation.

Cryptographic key management

A distributed computer system, has a number of users and target applications. When a user logs on to the system, an authentication unit issues the user with a privilege attribute certificate (PAC) representing the user's access rights. When the user wishes to access a target application, he presents the PAC to that application as evidence of his access rights. The application, in turn, passes the PAC to a PAC use monitor (PUM) which validates the PAC. The PUM is shared between a plurality of applications.

Access control in a distributed computer system

A mechanism is described for controlling access to a target application (TA) in a distributed computer system. A user sponsor (US) acting on behalf of an end user is issued with a privilege attribute certificate (PAC) containing initiator qualifier attributes (IQA) identifying permitted users of the PAC. The US obtains a key from a key distribution server (KDS), the key having initiator qualifier attributes of the US cryptographically associated with it. The US uses this key to communicate with the TA, and presents its PAC for verification. If the IQA in the PAC do not match the IQA associated with the key, this indicates that the PAC is being presented by the wrong initiator, and so access is not permitted. If a receiving entity subsequently wishes to act as an initiator and to use the PAC by proxy, it acquires a key from the KDS, the key having the receiving entity's attributes cryptographically associated with it. This provides a way of regulating proxy use of PACs.

Growing community of inventors

Calne, United Kingdom

Thomas Anthony Parker