Privacy preserving artificial immune system

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.

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, xγ,δ, δ where:
• x
• γ
• ,
• δ
• =
• {
• f
• ⁡
• (
• h
• .
• γ
• .
• δ
• ,
• k
• )
• if
• ⁢
• ⁢
• e
• y
• +
• δ
• .
• γ
• =
• p
• .
• γ
• δ
• +
• 1
• ⋀
• δ
• <
• n
• -
• 1
• -
• ∑
• i
• =
• 0
• n
• -
• 2
• ⁢
• f
• ⁡
• (
• h
• .
• γ
• .
• i
• ,
• k
• )
• if
• ⁢
• ⁢
• e
• y
• +
• δ
• .
• γ
• =
• p
• .
• γ
• δ
• +
• 1
• ⋀
• δ
• =
• n
• -
• 1
• r
• if
• ⁢
• ⁢
• e
• y
• +
• δ
• .
• γ
• ≠
• p
• .
• γ
• δ
• +
• 1
• ,
• n is the number of events in the anomalous pattern,
• p is the sequence of events in the anomalous pattern,
• e·y is an event of a type, y, observed at the node,
• h is a value of an identifier of a sequence of events,
• γ is an index value for an event in a sequence of events in the network of nodes,
• γ+δ is an index value for an event that occurs in a sequence of events δ steps in the sequence after an event having an index value of γ,
• k is a key value that is unknown to the system,
• i is a summation index,
• f is a cryptographic function, and
• r is a random number in the domain of f;
• and
• a processor configured to identify an anomalous pattern of events in the network, 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.