Detecting and confirming video piracy is a process, and fighting it involves an ecosystem. What’s become clear is that both of these are far-ranging propositions. From the media industry’s perspective, the CEO of FACT provides insights about fighting piracy in the U.K. From the technical perspective, there’s a new engineering approach that uses machine learning and artificial intelligence to help identify possible occurrences of piracy.
AI and machine learning for piracy detection
Certain approaches toward piracy detection have gained mindshare. One is to track the usage of credentials shared with friends and family by legitimate consumers; to detect possible theft of service when sharing falls outside of the terms of use. Another is content modification, to detect content that’s circulating or streaming outside of its licensed channels of distribution, coupled with monitoring to detect stolen content that’s identifiable via embedded watermarks or by matching extracted fingerprints.
But how can one identify pirate video streams without knowledge of the originating source, the intended destination, or without examining the content itself? For one answer, we can look to what’s going on in the network. An initiative aimed at identifying artificial intelligence and machine learning (AI/ML) best practices for the cable industry is underway at SCTE, the Society of Cable Telecommunications Engineers.
I was invited to attend a late-June conference call for the SCTE’s Artificial Intelligence and Machine Learning Working Group – whose presenter that day was Matt Tooley, NCTA’s vice president of broadband technology – on the topic of using AI and ML to detect pirate streaming.
An alternative to deep packet inspection
One of the better-known techniques for traffic analysis is deep packet inspection (DPI). While DPI can be used to identify infringing content by evaluating streaming payloads, Tooley said that operators haven’t deployed DPI network-wide or at scale for a multitude of reasons. As an alternative to DPI, he has been working on ways to use IP metadata to discern characteristics of IP streams without looking at the payload.
Under that approach, machine learning can be trained to identify packet flows that look like piracy without looking at IP addresses or the packet payload. If flows look suspicious, they can be flagged for further evaluation. Which begs the question: what does a “packet flow that looks like piracy” look like? As it turns out, IP flow durations, the number of packets in an IP flow, packet lengths, and inter-packet times can all be indicators if they fit certain patterns.
There are advantages to this approach since it is not looking at payload, which means it can help identify pirate video even if it is encrypted. It can identify pirated video that is inside an encrypted VPN tunnel as well as when the flow is encrypted using a protocol like HTTPS.
A promising work in progress
This AI/ML approach has been implemented experimentally but isn’t a product that a video provider can buy. It’s currently being evaluated for inclusion in a set of best practices that the SCTE is developing.
Ongoing refinements have reduced false-positive “detections” of piracy from about half, down to about 0.2%, and have increased its accuracy to about 97%. Efforts are also underway to make it more efficient computationally and to enable it to work at scale.
Certainly, it’s an initiative to monitor, which is something we all must do when it comes to piracy. Further details can be learned from a 2019 SCTE paper that Tooley co-wrote.
FACT fights piracy in the U.K.
Last month, this column reported about FACT, the U.K.-based Federation Against Copyright Theft, and its success in reducing links to illegal pirate streams. Since then, I was able to interview FACT CEO Kieron Sharp.
He explained that media companies and distributors in the U.K. have varying levels of awareness and urgency toward piracy. “Media giants like Sky, Virgin Media and BT Sport understand the importance of anti-piracy,” said Sharp. “They have a vested interest because they don’t just distribute the content; they often own it and they know just how valuable it is.”
Pay TV operators are increasingly concerned because sites and apps that aggregate TV programming and stream it to consumers via apps and Websites have become their biggest competition – as has been true in most pay TV market regions. He noted that concerns about piracy tend to reflect business conditions. When market share drops, video providers begin to pay attention.
Takedowns are an ongoing challenge
One of FACT’s services is to help bring takedown notices to online companies like Google, on behalf of private individuals. FACT boasts a 90% success rate in enforcing pirate take-downs. The other 10% is larger-scale pirates that are handled though alternative actions such as site blocking. A unique attribute of U.K. law is that private individuals have the right to prosecute piracy cases in the court system, and FACT sometimes acts as an advocate with them.
To be realistic, you can’t fully stop illegal streamers, but every takedown helps. “When illegal streams are taken down, we seek to display the FACT banner which then directs to sites that offer legal content,” said Sharp. “Even if a site comes back after it has been shut down, the pirate loses market share. So, it’s still a win.”
Asked for any pearls of wisdom, he said, “When it comes to piracy, you have to do something, you have to do it right away and you have to keep at it or the problem will return. We’re making progress, but there’s a ways to go.”
Steve Hawley is managing director of Piracy Monitor, which provides news and insights about video and audiovisual content piracy, and its effects on video providers, creative professionals and on consumers. Subscribe to the E-Newsletter to receive news and updates. Piracy Monitor is active in four areas: Piracy awareness, Market intelligence, Industry marketing and Consulting. Mr. Hawley is also a contributing analyst to Parks Associates and S&P Global Market Intelligence.
Industry Voices are opinion columns written by outside contributors—often industry experts or analysts—who are invited to the conversation by FierceVideo staff. They do not represent the opinions of FierceVideo.