Dr. Roman Yampolskiy has dedicated his career to the study of artificial intelligence, particularly AI safety. Being a scientist in the field of AI also requires a philosophical understanding of the subject, and Dr. Yampolskiy isn’t afraid to explore. His interests include AI Safety, Artificial Intelligence, Behavioral Biometrics, Cybersecurity, Digital Forensics, Games, Genetic Algorithms, and Pattern Recognition.
Related: Dr. Vesselin Bontchev: Non-Replicating Malware Has Taken over the Computer Virus
STF: What inspired you to look deeply into the subject of AI?
Dr. Yampolskiy: It is the technology which is going to impact everything and everyone. Appearance of Human Level AI will be the last invention we ever have to make and an unprecedented event in history.
STF: Tell me more about your book, Artificial Superintelligence: A Futuristic Approach. Was it challenging to create a future landscape for AI? Is your approach entirely scientific?
Dr. Yampolskiy: The book is part philosophy part computer science. It engages with questions in security, ethics, biology and many others.
Since we don’t have any superintelligent systems available for experimentation at this point most of the analysis we can perform is based on philosophy of mind and through experiments about concepts such as recursive self-improvement.
STF: How can we make “sure that emerging superintelligence is beneficial to humanity”? Should there be a mutual agreement between technology and ethics?
Dr. Yampolskiy: Making sure that AI is beneficial is the most interesting and important unsolved problem in science. It is likely that if we ever find a solution it will be at the intersection of ethics and technology.
STF: When do you see this happening?
Dr. Yampolskiy: Nobody knows how long it will take to create true AI, but a lot of people think it might happen by 2045.
STF: What can AI contribute to the evolution of cybersecurity?
Dr. Yampolskiy: Future attacks will frequently rely on AI tools and progressively will become fully automated. Hackers of tomorrow will be machines.
AI Safety can be improved based on ideas developed by cybersecurity experts. For narrow AIs safety failures are at the same, moderate, level of criticality as in cybersecurity, however for general AI, failures have a fundamentally different impact. A single failure of a superintelligent system may cause a catastrophic event without a chance for recovery. The goal of cybersecurity is to reduce the number of successful attacks on the system; the goal of AI Safety is to make sure zero attacks succeed in bypassing the safety mechanisms. Unfortunately, such a level of performance is unachievable. Every security system will eventually fail; there is no such thing as a 100% secure system.
STF: What do you think about the defense/prevention mechanism? Is AI helping improve cybersecurity?
Dr. Yampolskiy: AI has tremendous ability to help in all domains of interest and cybersecurity is not an exception. But just like AI can be used to detect and prevent attacks it can be used to detect novel vulnerabilities and help automate attacks.
Related: Raef Meeuwisse: Criminals Share Information Better and Faster than Legitimate Organizations
STF: What about AI and the future of other sectors such as health and entertainment? Where will technology end and human begin?
Dr. Yampolskiy: Definitely expect a lot of benefits from AI in healthcare, particularly via applications to genetic engineering both to cure most disorders and to design an improved human body. Initially technology and biology will merge and create cyborgs with a lot of special abilities, but eventually biology will become a bottleneck and will be removed from the future superintelligent agents.
STF: What Sci-Fi movies about AI have you seen that have stuck with you?
Dr. Yampolskiy: I don’t watch TV, but make exceptions for some movies. Terminator and Ex Machina are my all-time favorites.
STF: Can you see Ex Machina happening in real life?
Dr. Yampolskiy: Sex robots are already here and it is only a question of time before gullible people fall in love with artificial seductresses.
STF: What is next on your list of professional accomplishments?
Dr. Yampolskiy: I hope to one day win an Ig Nobel prize.
SensorsTechForum’s “Ask the Experts” Interview Series
If you are a cyber security expert and you want to share your experience with our audience, send us an email at support[at]sensorstechforum.com. We will gladly converse with you about anything cyber security!
Milena Dimitrova
An inspired writer and content manager who has been with SensorsTechForum since the project started. A professional with 10+ years of experience in creating engaging content. Focused on user privacy and malware development, she strongly believes in a world where cybersecurity plays a central role. If common sense makes no sense, she will be there to take notes. Those notes may later turn into articles! Follow Milena @Milenyim
Follow Me: