Artificial Intelligence

Aims At the end of the course students can: • understand the vulnerabilities and adversarial models for embedded (crypto) devices, and explain the objectives for protecting those devices against implementation attacks • explain currently known attacks on small devices and associated countermeasures; • carry out side-channel and fault injection attacks on smartcards i.e. microcontrollers. • use statistics and machine learning techniques when performing the attacks Content Our daily business relies on the devices we carry on us, such as bank, ID and transportation cards, car keys, and mobile phones. All those devices use secret (cryptographic) keys that are not accessible from the outside. Getting a hold of the key allows a hacker to steal our data or take control of a self-driving car or a pacemaker. The majority of real-world attacks on security implementations use side-channel analysis, i.e., they measure and process physical quantities, like the power consumption or electromagnetic emanations of a chip, or reaction time of a process. Preventing this kind of leakages and side-channel attacks in general remains a great challenge as effective mitigations are often prohibitively expensive in terms of power and energy resources. This course treats security aspects of embedded cryptographic device, including hardware and software, certification and security evaluation and the security objectives these are meant to provide, and attack techniques and countermeasures, especially side-channel and fault attacks. We cover all implementation attacks on embedded systems, including state of the art methods using machine/deep learning and fault injection. The course includes practical lab assignments where students perform the attacks on physical targets.