IT specialists from the Lower Saxony State Criminal Police Office (LKA) developed a neural network to detect (child) pornography.

The artificial intelligence (AI) is now being made available nationwide to investigators in the state of Lower Saxony as part of a one-year pilot phase in order to provide them with technical support in their extensive task in the fight against child pornography and, in the long term, to significantly reduce the processing time by reducing the number of files to be viewed to accelerate. Reports the Lower Saxony State Criminal Police Office via press release.

“I am proud that we are the first federal state to be able to use specially developed software to combat child pornography,”

said LKA President Friedo de Vries.

Child and youth pornography continues to increase

In recent years, child and youth pornographic content has increasingly been distributed on the Internet and digital media. According to preliminary evaluations, child sexual abuse cases increased by around 20 percent in 2019 compared to the previous year. There has been an increase of around 75 percent in the distribution of pornographic writings in Lower Saxony compared to 2018.

[mk_ad]

In addition, the data storage media seized during the investigations have increasingly larger storage capacities. In 2018 alone, the police in Lower Saxony seized data carriers with a total volume of around 1.3 petabytes. In addition to the enormous psychological strain, this means an almost impossible amount of effort for police processing, as the image and video material must be viewed and evaluated in its entirety.

The Lower Saxony Minister for the Interior and Sport, Boris Pistorius, says about the pilot project:

“We are doing everything we can to relieve the burden on the police forces who have to deal with child pornography files. We hope that the model project with artificial intelligence will significantly reduce the number of media files that our experts ultimately have to look at.

We also expect that this technology will enable investigations in this area to be completed much more quickly.”

Through the use of artificial intelligence, seized media material is separated into files with pornographic content and files without pornographic content and presented to the investigator as a pre-selection.

[mk_ad]

The success rate of the software, which was developed over the past two years January 16, 2020 Press Release No. 1 Press as part of a project at the LKA, is already on average over 96 percent when it comes to recognizing files with non-pornographic content .

“Our software is already achieving a success rate that has never been achieved in Germany and is far above the average for comparable applications. I am sure that we will contribute to significantly easing the burden on investigative departments in the future,”

said de Vries.

“With the help of our AI, it is possible to select the pornographic images and videos from the unstructured file juggernaut of the seized material and thus pass them on immediately for evaluation by the investigators. This saves us a lot of time!”

continued Friedo de Vries.

Software is used nationwide

From February, the new software will be available to police stations across the country to prioritize seized files. After the usual technical comparison with already known pornographic files, the selection will now take place in a further step using the software developed by the LKA. The appropriately classified files are then viewed and evaluated by the investigators.

[mk_ad]

As part of the pilot, the neural networks of artificial intelligence will be further checked and trained at the same time. That is why the results generated by the AI ​​will be continuously checked until the end of this year to see whether a correct distinction has been made between pornographic and non-pornographic content. Even after the completion of the pilot project, there are plans to continue developing the AI ​​software.

“We are aware of our special responsibility in this sensitive area of ​​crime and do not blindly trust the machines.”

said de Vries.

Interior Minister Pistorius concluded at today's press conference:

“We also have to provide digital answers to the digital challenges. With more and more staff alone, we can no longer counteract these heinous acts in the digital world. Relying on specialized personnel and technical solutions is absolutely the right way. Faster procedures can help to identify perpetrators more quickly – and protect victims.”

Related to the topic: Stop the spread of child pornography!

Source: Lower Saxony State Criminal Police Office
Article image: Shutterstock / Raihana Asral


If you enjoyed this post and value the importance of well-founded information, become part of the exclusive Mimikama Club! Support our work and help us promote awareness and combat misinformation. As a club member you receive:

📬 Special Weekly Newsletter: Get exclusive content straight to your inbox.
🎥 Exclusive video* “Fact Checker Basic Course”: Learn from Andre Wolf how to recognize and combat misinformation.
📅 Early access to in-depth articles and fact checks: always be one step ahead.
📄 Bonus articles, just for you: Discover content you won't find anywhere else.
📝 Participation in webinars and workshops : Join us live or watch the recordings.
✔️ Quality exchange: Discuss safely in our comment function without trolls and bots.

Join us and become part of a community that stands for truth and clarity. Together we can make the world a little better!

* In this special course, Andre Wolf will teach you how to recognize and effectively combat misinformation. After completing the video, you have the opportunity to join our research team and actively participate in the education - an opportunity that is exclusively reserved for our club members!


Notes:
1) This content reflects the current state of affairs at the time of publication. The reproduction of individual images, screenshots, embeds or video sequences serves to discuss the topic. 2) Individual contributions were created through the use of machine assistance and were carefully checked by the Mimikama editorial team before publication. ( Reason )