# US 2019/0356966 A1 · Method and Apparatus for Feedback-Based Piracy Detection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0356966 A1
- Document ID: US20190356966A1
- Status: Published application
- Kind: A1
- Application number: 16/529,606
- Filed: 2019-08-01
- Published: 2019-11-21
- Earliest claimed: 2018-02-03
- Assignees: Irdeto B.V.
- Applicants: Irdeto B.V.
- Inventors: Lau Zuydervelt; Vladimir Zivkovic; Maksym Koshel; Lucas Catranis; Yu Duan; Chunqiu Lu; Lin Yuan; Kimon Tsitsikas; Vyacheslav Shoshin
- Web page: https://patentgrep.com/patent/US20190356966A1

## CPC

- H04N 21/8358: involving watermark {(protecting executable software by watermarking G06F21/16; image watermarking in general G06T1/0021; watermarks inserted in still images for transmission purposes H04N1/32144; inserting watermarks during video coding H04N19/467)}
- G06T 1/0028: {Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking}
- G06T 1/005: {Robust watermarking, e.g. average attack or collusion attack resistant}
- H04N 21/26258: {for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list (retrieval of multimedia data based on playlists G06F16/40)}
- H04N 21/44236: {Monitoring of piracy processes or activities (protecting computer platforms against harmful, malicious or unexpected behaviour or activities using intrusion detection and counter measures G06F21/566; computer virus detection and handling G06F21/56)}
- H04N 21/4825: {using a list of items to be played back in a given order, e.g. playlists}
- H04N 21/8352: involving content or source identification data, e.g. Unique Material Identifier [UMID]
- H04N 21/8456: {by decomposing the content in the time domain, e.g. in time segments}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Watermarking of a content stream is accomplished in a session-based manner to provide watermarking based on a uniquely generated manifest that will result in a stream that allows for unique identification of information. The manifest specifies a sequence of watermarks for successive segments of a content stream designated for a specific receiver. The system and method leverages existing content distribution infrastructure and has many of the benefits of conventional head-end watermarking, allows unique identification of small segments of the data stream and reduces content distribution network storage requirements. Groups of nodes can be provided with unique watermark patterns and detection and watermark pattern reconfiguration can be accomplished in an iterative manner to find a specific node without the need to create unique watermark patterns for each node.

## Claims

### Claim 1

A method for detecting piracy of multiple content streams respectively associated with receivers, the method comprising:
detecting potential unauthorized use of a content stream having a first predetermined watermark pattern defined by a sequence of watermarks applied to successive elements of the content stream by a watermarking system, wherein the predetermined watermark pattern has been transmitted to multiple nodes in a first group;
dividing the first group into at least two subgroups of nodes each subgroup being smaller than the first group;
transmitting information regarding the at least two subgroups to the watermarking system to thereby allow the watermarking system to watermark further elements of the content stream to define a second predetermined watermark pattern to a first subgroup of nodes of the at least two subgroups and a third predetermined watermark pattern to a second subgroup of nodes of the at least two subgroups; and
detecting unauthorized use of a content stream having the second predetermined pattern to thereby determine that a node in the first subgroup is the source of the unauthorized use.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
dividing the first subgroup into at least two further subgroups of nodes, each further subgroup being smaller than the first subgroup;
transmitting information regarding the at least two further subgroups to the watermarking system to thereby allow the watermarking system to watermark further elements of the content stream to define a fourth predetermined watermark pattern to a first further subgroup of nodes of the at least two further subgroups and a fifth predetermined watermark pattern to a second further subgroup of nodes of the at least two further subgroups; and
detecting unauthorized use of a content stream having the fourth predetermined pattern to thereby determine that a node in the first further subgroup is the source of the unauthorized use.

### Claim 3 (depends on 1)

The method of claim 1, wherein the watermarking system created each predetermined watermark pattern by:
(a) receiving from a receiver a request for the content stream;
(b) in response to the request for the content stream, obtaining a watermark sequence associated with the request, the watermark sequence indicating successive watermarks to be respectively applied to successive segments of the content stream provided in response to the request;
(c) receiving a request for a specified content segment of the content stream;
(d) returning, as a watermarked segment, the specified content segment with the watermark specified by the watermark sequence;
(e) repeating steps (c) and (d) for successive content segments of the content stream; and
(f) packaging the watermarked content segments to create a content stream.

### Claim 4 (depends on 3)

The method of claim 3, wherein the request includes receiver identification information and wherein the watermark sequence is associated with the request based on the receiver identification information.

### Claim 5 (depends on 3)

The method of claim 3, wherein the watermark sequence is one of plural watermark sequences stored in a manifest.

### Claim 6 (depends on 3)

The method of claim 3, wherein the watermark sequence is associated with the request based on receiver identification information in the manifest.

### Claim 7 (depends on 3)

The method of claim 3, wherein said returning comprises embedding the watermark specified by the sequence in an instance of the content segment.

### Claim 8 (depends on 3)

The method of claim 3, wherein the watermark sequence associated with the receiver is generated in response to the request for content.

### Claim 9 (depends on 3)

The method of claim 3, wherein obtaining a watermark sequence associated with the request comprises receiving the request for content from the client and returning the watermark sequence as manifest data to the client, whereby the client uses the manifest data to generate the request for a specified content segment.

### Claim 11 (depends on 1)

The method of claim 1, wherein detecting comprises extracting a watermark pattern from a content stream.

### Claim 12

A computer system for detecting piracy of multiple content streams respectively associated with receivers, the system comprising:
at least one processor; and
at least one memory operatively coupled to the at least one processor and storing computer executable instructions which, when executed by the at least one processor, cause the at least one processor to:
detect potential unauthorized use of a content stream having a first predetermined watermark pattern defined by a sequence of watermarks applied to successive elements of the content stream by a watermarking system, wherein the predetermined watermark pattern has been transmitted to multiple nodes in a first group;
divide the first group into at least two subgroups of nodes each subgroup being smaller than the first group;
transmit information regarding the at least two subgroups to the watermarking system to thereby allow the watermarking system to watermark further elements of the content stream to define a second predetermined watermark pattern to a first subgroup of nodes of the at least two subgroups and a third predetermined watermark pattern to a second subgroup of nodes of the at least two subgroups; and
detect unauthorized use of a content stream having the second predetermined pattern to thereby determine that a node in the first subgroup is the source of the unauthorized use.

### Claim 13 (depends on 12)

The system of claim 12, wherein the instructions further cause the at least one processor to:
divide the first subgroup into at least two further subgroups of nodes, each further subgroup being smaller than the first subgroup;
transmit information regarding the at least two further subgroups to the watermarking system to thereby allow the watermarking system to watermark further elements of the content stream to define a fourth predetermined watermark pattern to a first further subgroup of nodes of the at least two further subgroups and a fifth predetermined watermark pattern to a second further subgroup of nodes of the at least two further subgroups; and
detect unauthorized use of a content stream having the fourth predetermined pattern to thereby determine that a node in the first further subgroup is the source of the unauthorized use.

### Claim 14 (depends on 12)

The system of claim 12, wherein the watermarking system created each predetermined watermark pattern by:
(a) receiving from a receiver a request for the content stream;
(b) in response to the request for the content stream, obtaining a watermark sequence associated with the request, the watermark sequence indicating successive watermarks to be respectively applied to successive segments of the content stream provided in response to the request;
(c) receiving a request for a specified content segment of the content stream;
(d) returning, as a watermarked segment, the specified content segment with the watermark specified by the watermark sequence;
(e) repeating steps (c) and (d) for successive content segments of the content stream; and
(f) packaging the watermarked content segments to create a content stream.

### Claim 15 (depends on 4)

The system of claim 4, wherein the request includes receiver identification information and wherein the watermark sequence is associated with the request based on the receiver identification information.

### Claim 16 (depends on 14)

The system of claim 14, wherein the watermark sequence is one of plural watermark sequences stored in a manifest.

### Claim 17 (depends on 14)

The system of claim 14, wherein the watermark sequence is associated with the request based on receiver identification information in the manifest.

### Claim 18 (depends on 14)

The system of claim 14, wherein said returning comprises embedding the watermark specified by the sequence in an instance of the content segment.

### Claim 19 (depends on 14)

The system of claim 14, wherein the watermark sequence associated with the receiver is generated in response to the request for content.

### Claim 20 (depends on 14)

The system of claim 14, wherein obtaining a watermark sequence associated with the request comprises receiving the request for content from the client and returning the watermark sequence as manifest data to the client, whereby the client uses the manifest data to generate the request for a specified content segment.

### Claim 22 (depends on 12)

The system of claim 12, wherein detecting comprises extracting a watermark pattern from a content stream.
