Alyssa Miller - Reality Lost - Deepfakes Changing the Face of Attacks смотреть
Наш мир невероятно динамичен и новости типа "Alyssa Miller - Reality Lost - Deepfakes Changing the Face of Attacks" появляются практически каждую секунду, успевай лишь смотреть онлайн.
Recorded on May 1st, 2020 at the 6th annual BSides Knoxville (virtual this year) conference
As a result of continuing advancements in neural networks, deep fake media has become increasingly convincing and easy to produce. Experts have warned of the impact this could have on elections and personal security. Additionally, deepfakes also pose very real threats to businesses and global markets, although these threats receive far less attention.
In this session we will analyze the technology behind creating deep fake media, showing how Generative Adversarial Networks (GAN) create convincing fake videos and audio from very limited samples. Attendees will see how the nature of GANs completely shifts the way we think about security defense, when the defender is actually designed to train the attacker to improve their attacks. The presentation will examine research into deepfake detection methods and also present breaking research being conducted to develop proactive countermeasures such as Adversarial Perturbations. Attendees will see how simple technology can defeat facial recognition algorithms that deepfake generation relies on.
To conclude the session, practical steps that organizations and individuals can take to defend themselves from deepfakes will also be presented. Additionally, legitimate and promising applications of this technology will also be shared. From its use in entertainment, to improved analysis of medical imaging and even how GANs are being leveraged in malware identification, attendees will be left with a comprehensive understanding of the technology and the threats and promise it represents in the future.