{"id":36230,"date":"2020-07-23T14:00:00","date_gmt":"2020-07-23T14:00:00","guid":{"rendered":"https:\/\/www.darkreading.com\/operations\/deepfakes-and-james-bond-research-project-cool-but-dangerous\/a\/d-id\/1338370"},"modified":"2020-07-23T14:00:00","modified_gmt":"2020-07-23T14:00:00","slug":"deepfakes-james-bond-research-project-cool-but-dangerous","status":"publish","type":"post","link":"https:\/\/www.threatshub.org\/blog\/deepfakes-james-bond-research-project-cool-but-dangerous\/","title":{"rendered":"Deepfakes & James Bond Research Project: Cool but Dangerous"},"content":{"rendered":"
<\/header>\n

Open source software for creating deepfakes is getting better and better, to the chagrin of researchers<\/span><\/p>\n

In January 2020, NCC Group collaborated with University College London (UCL) students on the topic of cybersecurity implications of deepfakes<\/a>. As part of our wider research into artificial intelligence (AI) and machine learning, we continue to explore the potential impact of deepfakes in a cybersecurity context<\/a>, particularly around their use in nefarious activities. There have already been numerous stories of real-world fraudsters using AI to mimic CEO voices in cybercriminal activities, and we believe it’s only a matter of time before we see similar, visual-based attempts using deepfake frameworks. And remember, many of those frameworks are open source and freely available for experimentation.<\/p>\n

Project & Challenge<\/strong>
Our brief to the students (who are part of UCL’s Centre for Doctoral Training in Data Intensive Science) was to explore common open source deepfake frameworks and broadly assess them in terms of ease of use and quality of faked outputs. This first part of the research was to help us understand how accessible these frameworks are to potential fraudsters, and the computational resources and execution times needed to produce realistic outputs. We examined two in particular, FaceSwap<\/a> and DeepFaceLab<\/a>, and one open source speech-driven facial synthesis model<\/a>.<\/p>\n

We also asked them to help us explore the practicalities \u2014 specifically, how realistic fake videos can be achieved. The challenge was to take a three-minute clip from a movie (Casino Royale<\/em>) and replace the face of the lead character (Daniel Craig playing James Bond) with my face. This helped us understand logistical aspects around source and destination video qualities, lighting conditions, angles, and facial expressions of source and target imagery. We also got a better understanding of not only the technical details but also the procedural and physical aspects.<\/p>\n

On the procedural front, we learned that when trying to create realistic deepfakes, the quality (resolution) of source and destination image sets is very important, in that they should match very well. We lost some realism in the output because the initial HD quality source footage didn’t match the cinematic effect of the target video, which had a smoother resolution. Lighting conditions are also important, and both source and target faces should be similar in shape. For example, our source image had to be slightly stretched to match that of the James Bond character.<\/p>\n

Everyday objects also presented difficulties \u2014 the simple act of wearing glasses could make it easier to prevent deepfake attacks. <\/p>\n

Procedurally, we also learned that it’s harder to produce realistic deepfakes when the source image doesn’t have the same types of mouth shape and movement (during dialogue) and eye movements related to raised eyebrows or blinking. Attackers seeking to create realistic deepfakes need a rich source facial image dataset of each individual with different facial expressions and angles.<\/p>\n

What We Learned<\/strong>
Our research was designed to help us better understand technical risk mitigation strategies and\/or policies, regulation, and legislation that might be needed to curb potential abuse of deepfake technology. Here’s what we found:<\/p>\n