When we introduced Magnet.AI at this time last year, we were proud to be the first in the industry to introduce contextual chat content classification. One year later, Magnet AXIOM is still the only digital forensics tool that uses machine learning to identify messages that contain potential illicit content—and we’re proud to add new classifiers as of AXIOM 2.0.
Not only has the popularity of chat and email applications resulted in a massive spike of text-based conversations; but an increasing number of devices (smartphones, digital cameras, other IoT devices, etc.) also facilitate the easy capture of photos and videos.
As a result, the number of pictures and messages that may appear in a case has grown exponentially, making it difficult for forensic examiners, investigators and analysts to keep up. The manual analysis of the evidence for context and relevance, combined with report building, can add significant time to an investigation.
Magnet.AI allows an examiner or investigator to better prioritize their time in an investigation, and find potentially relevant evidence faster than they could through manual review.
New Photo, Text Classification in Magnet.AI
With the launch of AXIOM 2.0, the Magnet.AI module now identifies images that may contain depictions of child sexual abuse, nudity, weapons, and drugs. We’ve also expanded our text classification model to detect potential sexual conversations in addition to child luring (both in the English language).
This combination of picture-based and text-based classification means that corporate as well as law enforcement investigators can now benefit from Magnet.AI:
- Law enforcement now has an even stronger way to obtain key evidence for drug, child exploitation, human trafficking and gang investigations.
- Corporate investigators responsible for employee misconduct investigations can use potential pornographic and drug images, as well as potential sexual conversations, to ascertain whether harassment or other misconduct is happening.
Changes to the Magnet.AI Workflow
When we introduced Magnet.AI, it ran automatically when you opened your case in AXIOM Examine. You indicated to us that this could be a problem in some cases: if it revealed evidence that was outside the scope of your warrant, your examination would have to wait until you could apply for a new warrant to examine this data, too, or else risk the admissibility of all the evidence on the device.
In response, we’ve removed automatic AI processing upon case open, and replaced it with a post-processing task in AXIOM Examine. You can select to run Magnet.AI on all case evidence, or a subset of specific content, depending on the scope of your warrant. You can also select which models (out of those listed above) you want to run, and you can customize the tags used to classify the data. There is now also a job status indicator to show Magnet.AI’s progress.
Finally, all results found and tagged by Magnet.AI can be included in a Portable Case for you to share with investigators.
Coming Soon for Magnet.AI
Over the next few months, look for additional text-based and picture capabilities to be added to Magnet.AI (and subscribe to our blog and/or newsletter to receive the news about these updates).
The Magnet.AI module will remain free of charge until January 2019. After that point, only child luring detection will remain free. If you aren’t currently using Magnet.AI and you’d like to experience how it helps you discover relevant picture and chat evidence faster than you could with a manual review, contact us for a free demo.