PRIVACY PRESERVING ARTIFICIAL IMMUNE SYSTEM

• US 20110137800A1
• Filed: 12/08/2009
• Published: 06/09/2011
• Est. Priority Date: 12/08/2009
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP AG (SAP SE)
• Inventors: Oertel, Nina, Kerschbaum, Florian
• Granted Patent: US 8,015,080 B2
• Time in Patent Office: Days
• US Class Current: 705/50
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders

Abstract

Identifying anomalous products in a supply chain includes maintaining a set of anomalous patterns of events products in the supply chain. At least one of the anomalous patterns of events is transmitted to nodes of the supply chain. Messages are received from nodes at a third party and indicate whether an event of the product in the supply chain at the node matches an event in the anomalous pattern of events that has been transmitted to the node. Messages indicating that an event at the node matches an event in the anomalous pattern of events are securely encrypted, based on a key that is unknown to the third party, prior to transmission to the third party. A determination is made whether the product is an anomalous product, based on the messages from nodes indicating that a sequence of events occurring at one or more nodes matches a sequence of events in the anomalous pattern of events.

Claims

1. A computer-implemented method of identifying an anomalous product in a supply chain, the method comprising:

maintaining a set of anomalous patterns of events of a product in the supply chain;

transmitting at least one of the anomalous patterns of events to nodes of the supply chain;

receiving messages from nodes that have received the at least one pattern at a third party, wherein the third party is not a node of the supply chain, the messages indicating whether or not the occurrence of an event of the product in the supply chain at the node matches an event in the anomalous pattern of events that has been transmitted to the node, wherein messages indicating that an event at the node matches an event in the anomalous pattern of events are securely encrypted by the node prior to transmission to the third party, wherein the encryption is based on a key that is unknown to the third party; and

determining, via at least one processor of the third party, that the product is an anomalous product, wherein the determination is based on the messages from nodes indicating that a sequence of events occurring at one or more nodes matches a sequence of events in the anomalous pattern of events.

2. The method of claim 1, further comprising generating at least some of the patterns of events, wherein the generation of an anomalous pattern of events includes:

determining possible patterns of events of a product in the supply chain;

comparing the possible patterns of events to a set of patterns that are known to be nonanomalous; and

selecting possible patterns that do not match a pattern that is known to be non-anomalous for the set of anomalous patterns of events.

3. The method of claim 2, further comprising:

determining a pattern of events in the supply chain to be a non-anomalous pattern of events by;

receiving, at the third party, messages from nodes of the supply chain indicating a pattern of an actual product in the supply chain, wherein the pattern is known to be non-anomalous.

4. The method of claim 1, wherein the messages include information about an action performed on the product and the node that performs the action.

5. The method of claim 1, wherein messages received from a node are securely encrypted by applying a cryptographic hash function to information contained in the message, wherein the hash function uses a key known to each of the nodes of the supply chain.

6. The method of claim 5, wherein the key is not known by the third party.

7. The method of claim 1, wherein messages indicating that an event at the node does not match an event in the anomalous pattern of events contain random information.

8. The method of claim 1, wherein the messages received from a node indicating that the occurrence of an event of the product in the supply chain at the node matches an event in the anomalous pattern include cryptographically encrypted information about the position of the event in a sequence of events for the product in the supply chain and about the position of the event in the anomalous pattern of events that has been transmitted to the node and unencrypted information about the position of the event in the anomalous pattern of events.

9. The method of claim 8, further comprising:

sorting the received messages indicating that the occurrence of an event of the product in the supply chain at the node matches an event in the anomalous pattern by the information about the position of the event in the anomalous pattern of events; and

determining whether a combination of information from the sorted messages indicates that a sequence of events for the product in the supply chain matches the anomalous pattern of events.

10. The method of claim 1, the messages received from a node include pairs of values, x_γ

,δ

, δ

where;

11. The method of claim 10, wherein f is a cryptographic hash function.

12. The method of claim 10, wherein determining whether the product is an anomalous product based on the messages from nodes indicating that an event at the node matches an event in the anomalous pattern of events further comprises:

sorting received pairs of values by δ

; and

determining whether a combination of x<sub>γ

,δ</sub>

values corresponding to sequentially sorted δ

values yield a non-random result.

13. The method of claim 10, wherein the product includes a tag that stores updatable information about the value of γ

.

14. A system for identifying an anomalous product in a supply chain, the system comprising:

a memory storing a set of anomalous patterns of events of a product in the supply chain;

a transmission engine configured for transmitting at least one of the anomalous patterns of events to nodes of the supply chain;

a message handler configured for receiving messages from nodes that have received the at least one pattern, the messages indicating whether or not the occurrence of an event of the product in the supply chain at the node that sends a message matches an event in the anomalous pattern of events that has been transmitted to the node, wherein messages indicating that an event at the node matches an event in the anomalous pattern of events are securely encrypted prior to receipt by the message handler, wherein the encryption is based on a key that is unknown to the system; and

a processor configured to determine that the product is an anomalous product, wherein the determination is based on the messages from nodes indicating that a sequence of events occurring at one or more nodes matches a sequence of events in the anomalous pattern of events.

15. The system of claim 14, further comprising:

sorting the received messages indicating that the occurrence of an event of the product in the supply chain at the node matches an event in the anomalous pattern by the information about the position of the event in the anomalous pattern of events; and

determining whether a combination of information from the sorted messages indicates that a sequence of events for the product in the supply chain matches the anomalous pattern of events.

16. The system of claim 14, wherein received from a node include pairs of values, x_γ

,δ

, δ

where;

17. The system of claim 16, wherein f is a cryptographic hash function.

18. The system of claim 16, wherein the processor is further configured to determine whether the product is an anomalous product based on the messages from nodes indicating that an event at the node matches an event in the anomalous pattern of events by:

sorting received pairs of values by δ

; and

determining whether a combination of x<sub>γ

,δ</sub>

values corresponding to sequentially sorted values yields a non-random result.

19. A system for identifying an anomalous pattern of events in a network of nodes, the system comprising:

a memory storing a set of anomalous patterns of events in the network of nodes;

a transmission engine configured for transmitting at least one of the anomalous patterns of events to nodes of the network of nodes;

a message handler configured for receiving messages from each of the nodes at a third party that is not a node of the network, the messages indicating whether or not the occurrence of an events in the network at the node matches an event in the anomalous pattern that has been transmitted to the node, wherein messages indicating that an event at the node matches an event in the anomalous pattern of events are securely encrypted by the node prior to receipt by the message handler, wherein the encryption is based on a key that is unknown to the system, the messages received from a node including pairs of values, x<sub>γ

,δ</sub>

, δ

where;

20. The system of claim 19, wherein the processor is further configured to determine whether a sequence of occurrences of events is an anomalous pattern based on the messages from nodes indicating that an event at the node matches an event in the anomalous pattern of events by:

sorting received pairs of values by δ

; and

determining whether a combination of x<sub>γ

,δ</sub>

values corresponding to sequentially sorted values yields a non-random result.