Secure AI Weekly

As smart systems become increasingly common in the realm of national security, risk issues require more attention Immune to hacks: Inoculating deep neural networks to thwart attacks University of Michigan , March 24, 2022 Have you ever wondered what the aftermath might be a situation where an intruder changes road ...

AI errors can lead to various incidents, which is why it is so important to monitor the safety and ethics of smart systems A promising defense against face biometrics scraping comes up short Biometric Update, March 18, 2022 The researchers considered that digital photographs, especially those common on the Internet, ...

As smart systems become increasingly common in the realm of national security, risk issues require more attention The benefits of peripheral vision for machines  MIT News, March 2, 2022 There are a number of similarities between the way some computer vision systems process images and the way humans see out ...

ML models not as secure as it might seem at first glance People Trust Deepfake Faces More Than Real Faces Vice, February 22, 2022 Faces created by artificial intelligence become so believable that they blur the line between real photos and fakes, even people sometimes find it difficult to distinguish ...

Collecting personal data such as selfies is not as secure as it might seem at first glance Machine Learning in 2022: Data Threats and Backdoors? Dark Reading, February 16, 2022 According to experts, in 2022, attackers will focus on disclosing data and finding ways to deceive algorithms. Machine learning algorithms ...

Sometimes artificial intelligence should be significantly upgraded  Facial recognition software used by the government is so flawed one man was able to ‘cheat California out of $900,000 in fake unemployment payments by posting pix of himself in a curly ginger wig’ Mail Online, February 11, 2022 An American allegedly used ...

New rules could greatly improve the ethical use of artificial intelligence China wants deepfake providers to be responsible for their creations Protocol, February 3, 2022 The Cyberspace Administration of China has published a new draft. Under the new bill, new oversight obligations will be imposed on deepfake technology developers. The ...

Sometimes artificial intelligence is not as smart as we think Bad Robot: the rise of adversarial AI Techinformed, January 27, 2022 While today smart systems are used to protect an organization from cyberattacks, attackers also use them in attacks. This is how a relatively new type of threats appeared under ...

Keep an eye on Digital ID attacks –  your face ID can be exploited by malefactors   This simple trick makes drones hallucinate  sUAS News, January 17, 2022 Researchers have learned how to find security vulnerabilities in camera systems on autonomous vehicles so that problems can be resolved. According to Yan, ...