On one of the hot days of summer in 2031, a confidential report leaked on social media caused massive protests in the midwest. The report stated that the AI judgment algorithm sentenced 112 black people to life imprisonment wrongly in the past year. Protestors tried to burn the state buildings. Another group attacked the offices of AI Companies in silicon valley. They chanted, ” Burn racist computers.”
The intelligence community believes that Russian state-sponsored hackers shared the report. But who cares? Many innocent people prisoned unfairly. The country is divided, and different ethnic groups are fighting with each other. The whole country is in chaos. People want their dream country, but a young computer scientist thinks protestors and the intelligence community are on the wrong track.
He had developed a special Data Anomaly Detector; he ran the program to scan AI system open data. After one month, He found out that some hackers altered the data and made AI sensitive to certain words. His report surprised the public opinion. It was an AI input attack. Who is behind this attack?
After one year, the intelligence community found that CCP sponsored hackers altered the African American suspect cases to deepen the racial divide. The other goal of the hackers was to undermine the free world institutions. And at the end, the young computer specialist of our story launched his unicorn startup.
http://futureportal.org/wp-content/uploads/2020/05/FuturePortal-300x138.png00Amir-reza Asadihttp://futureportal.org/wp-content/uploads/2020/05/FuturePortal-300x138.pngAmir-reza Asadi2021-04-17 08:50:592021-04-17 08:59:45an AI Attack to Free World
Phishing, ransomware, DDoS, Viruses, and Attack vectors are the most common cyber attack type(1). With the expansion of using AI in It’s predictable, we see more and more AI attacks shortly.
These “AI attacks” are fundamentally different from traditional cyberattacks(2), and current approaches are using against current cyberattacks that may not be appliable. AI Attacks may follow below goals:
Cause Damage: the attacker wants to cause damage by having the AI system malfunction. An example of this is an attack to cause an autonomous vehicle to ignore stop signs.
Hide Something: the attacker wants to evade detection by an AI system.
Degrade Faith in a System: the attacker wants an operator to lose faith in the AI system
Currently, The most common method used in AI Attacks is input attack, which makes a compromised AI system. It refers to manipulating what is fed into the AI system to alter the system’s output to serve the attacker’s goal(2).
We may see the following products in the near future:
Data Anomaly Detector made by computer security companies
AI training security certificate that ensures the quality of the AI System. (Five Star AI System ).