Hacking humans made easy: Signal processing + AI + video

David Maman will deliver a lecture on the critical importance of signal processing in data science management, at the upcoming Artificial Intelligence Conference, Beijing, June 20, 2019. Please see below a summary of the lecture. Looking forward to welcome you in our audience!

Remote analysis of someone’s health state for potential manipulation has gotten easier. Measuring body language, eye movement, and even pulse is possible—all you need is a video camera and some specialized algorithms. You don’t even need to hijack their phone or security camera at work. You can simply pretend to be taking a selfie when actually recording a video.

David Maman demonstrates the efficacy of signal processing and machine learning using video and remote photo plethysmography (PPG) heart-rate detection and the transformation to heart-rate variability (HRV) to discuss how easy it will be to hack humans. PPG is a non-invasive, low-cost, simple, optical technique that detects blood volume changes in the microvascular bed of tissue. After the recording is complete, the PPG information is transformed into HRV using multiple denoising mechanisms. HRV has been shown to correlate to risk of sudden death from a stroke (CVA), cognitive function, insulin sensitivity, inflammatory markers, visceral fat, aerobic fitness levels, fatigue markers and overtraining, performance, and others. The analysis can reveal a plethora of vital information, including cortisol levels (the catabolic stress hormone), cognitive function, insulin sensitivity, aerobic fitness, and indexes of fatigue or overtraining such as inflammatory markers. This, in turn, provides indicators about insulin levels.

By recognizing and leveraging these factors, attacks can occur without any direct physical contact. The possibilities are both obvious and ominous. Someone with high cortisol levels, heart rate, and blood pressure could be submitted to high levels of unattributable stressors. Fatigue, cognitive deficits, and poor fitness levels render openings to hackers in other ways. Direct physical intervention is possible if someone is fatigued and thus easily distracted. A simple drink containing concentrated sugar can put an insulin-sensitive person into a coma. The possibility that you could get “cyberwhacked” is probably already here. All the tools are in place; we just may not know when it happens. After all, if a guy with a heart condition, high blood pressure, inflammatory markers, and a high-stress job just happens to keel over…

The AI behind HRV: the critical role of signal processing in modern data science applications. Backed by centuries of proven mathematical applications, when signal processing is applied to data preparation, it accelerates delivery of the right answers to critical questions. Signal processing eliminates noise and prepares data for machine learning and artificial intelligence, significantly reducing false positives and delivering actionable results.

David Maman is founder, CEO, and CTO at Binah.ai. A serial entrepreneur, David founded Hexatier/GreenSQL (acquired by Huawei), Precos, Vanadium-soft, GreenCloud, Teridion, Terrasic, and Re-Sec, among others. Previously, he was a director in Fortinet’s CTO office, where he managed information security at Israeli telecom Bezeq. He has 24 years’ experience in leadership, AI, cybersecurity, development, and networking and is a veteran of an elite IDF unit. He was named one of the top 40 Israeli internet startup professionals by TheMarker Magazine and one of the top 40 under 40 most promising Israeli business professionals by Globes magazine. David holds a master’s degree in computer science from Open University.