Forensics is on the cusp of a third revolution in its relatively young lifetime. The first revolution, under the brilliant but complicated mind of J. Edgar Hoover, brought science to the field and was largely responsible for the rise of criminal justice as we know it today. The second, half a century later, saw the introduction of computers and related technologies in mainstream forensics and created the subfield of digital forensics.
We are now hurtling headlong into the third revolution with the introduction of Artificial Intelligence (AI) – intelligence exhibited by machines that are trained to learn and solve problems. This is not just an extension of prior technologies. AI holds the potential to dramatically change the field in a variety of ways, from reducing bias in investigations to challenging what evidence is considered admissible.
AI is no longer science fiction. A 2016 survey conducted by the National Business Research Institute (NBRI) found that 38% of enterprises are already using AI technologies and 62% will use AI technologies by 2018. “The availability of large volumes of data—plus new algorithms and more computing power—are behind the recent success of deep learning, finally pulling AI out of its long winter,” writes Gil Press, contributor to Forbes.com.
Digital forensics is ripe for disruption by AI technologies. Investigators have an increasingly large and complicated pool of data to sift through, from e-communication and social media to video footage and smart sensors, and they have less time and budget to handle these increased demands. “Digital forensics is an area that is becoming increasingly important in computing and often requires the intelligent analysis of large amounts of complex data,” concluded a study published by Digital Evidence & Electronic Signature Law Review. “It would therefore seem that AI is an ideal approach to deal with many of the problems that currently exist in digital forensics.”
AI technologies have already made their way into digital forensics, even if they were not marketed as such. Sophisticated algorithms are used today for DNA sequence matching, e-discovery document review, and cyber-crime detection, and more use cases are in the works. Some researchers are exploring how AI can facilitate improved collaboration when it comes to the analysis of cyber-crimes around the world. Others are experimenting with how AI can assist with recognizing patterns in the programming signatures of suspected criminals or wayward employees.
AccessData is working to stay on the forefront of this revolution with advances in its own capabilities. AccessData’s AD Lab, a powerful software platform for managing digital forensics investigations, provides investigators with an “intelligent assistant” that allows them to process sensitive forensic information with only minimal technical knowledge about the hardware from which the data is being collected or the software that is doing the actual evidence processing. Digital forensic examiners use the software to conduct searches for documents, images, addresses, social security numbers, etc., and the tool then guides the examiner through the analysis and processing of the data.
We’re still in the early stages of seeing how machine learning can bring greater efficiencies and deeper insights to digital forensics investigations. But the future of AI has clearly arrived. We have a unique opportunity to transform our field for the better.
Matt Coatney is a technology executive, business advisor, entrepreneur, author and speaker. His focus is bringing advanced technologies to market in the fields of Artificial Intelligence and analytics. He has co-founded three companies and advised several others, been an early-stage employee of two successful tech startups, and launched data analytics products for life sciences, healthcare, government, finance and law. Matt writes and speaks frequently on business and advanced technologies.
Matt’s e-course on the Business of Deep Learning, Machine Learning and AI is available on O’Reilly Media here: http://shop.oreilly.com/product/0636920063056.do.
Visit Matt on LinkedIn at https://www.linkedin.com/in/mattcoatney/.