Abstract
According to the 2020 cyber threat defence report, 78% of Canadian organizations experienced at least one successful cyberattack in 2020. The consequences of such attacks vary from privacy compromises to immersing damage costs for individuals, companies, and countries. Specialists predict that the global loss from cybercrime will reach 10.5 trillion US dollars annually by 2025. Given such alarming statistics, the need to prevent and predict cyberattacks is as high as ever. Our increasing reliance on Machine Learning(ML)-based systems raises serious concerns about the security and safety of these systems. Especially the emergence of powerful ML techniques to generate fake visual, textual, or audio content with a high potential to deceive humans raised serious ethical concerns. These artificially crafted deceiving videos, images, audio, or texts are known as Deepfakes garnered attention for their potential use in creating fake news, hoaxes, revenge porn, and financial fraud. Diversity and the widespread of deepfakes made their timely detection a significant challenge. In this paper, we first offer background information and a review of previous works on the detection and deterrence of deepfakes. Afterward, we offer a solution that is capable of 1) making our AI systems robust against deepfakes during development and deployment phases; 2) detecting video, image, audio, and textual deepfakes; 3) identifying deepfakes that bypass detection (deepfake hunting); 4) leveraging available intelligence for timely identification of deepfake campaigns launched by state-sponsored hacking teams; 5) conducting in-depth forensic analysis of identified deepfake payloads. Our solution would address important elements of the Canada National Cyber Security Action Plan(2019-2024) in increasing the trustworthiness of our critical services.
Abstract (translated)
URL
https://arxiv.org/abs/2211.14667
