Computer Sciences

A deep learning technique to generate DNS amplification attacks

Deep learning techniques have recently proved to be highly promising for detecting cybersecurity attacks and determining their nature. Concurrently, many cybercriminals have been devising new attacks aimed at interfering ...

Computer Sciences

Protecting computer vision from adversarial attacks

Advances in computer vision and machine learning have made it possible for a wide range of technologies to perform sophisticated tasks with little or no human supervision. From autonomous drones and self-driving cars to medical ...

Internet

'Trojan Source' bug a novel way to attack program encodings

A pair of security experts at TrojanSource have found a novel way to attack computer source codeā€”one that fools a compiler (and human reviewer) into thinking code is safe. Nicholas Boucher and Ross Anderson, both with the ...

Computer Sciences

A method to protect audio classifiers against adversarial attacks

In recent years, machine learning algorithms have attained remarkable results in a variety of tasks, including the classification of both images and audio files. A class of algorithms that has proven to be particularly promising ...

Computer Sciences

Hey, Alexa: Sorry I fooled you

A human can likely tell the difference between a turtle and a rifle. Two years ago, Google's AI wasn't so sure. For quite some time, a subset of computer science research has been dedicated to better understanding how machine ...

page 1 from 2