Skip to main content

Covid-19 Notice

All campus events (including Division of Extension sponsored events outside of Dane County) are canceled through June 30, with limited exceptions to be granted by deans or vice chancellors. Even if an event is not yet labeled as canceled, it's likely to be canceled, postponed or modified to online only, from now through June 30. Please check with organizers before attending.

Processor Hardware Security Detection by Unique Program Execution Checking — Wolfgang Kunz

Event Details

Tuesday, April 9, 2019
11 a.m.-12 p.m.

Recent discovery of security attacks in advanced processors, known as Spectre and Meltdown, has resulted in high public alertness about security of hardware. The root cause of these attacks is information leakage across covert channels that reveal secret data without any explicit information flow between the secret and the attacker. Many sources believe that such covert channels are intrinsic to highly advanced processor architectures based on speculation and out-of-order execution, suggesting that such security risks can be avoided by staying away from high-end processors. This talk, however, presents research results which show that the problem is of wider scope: we present a new class of covert channel attacks which are possible in average-complexity processors with in-order pipelining, as they are mainstream in applications ranging from Internet-of-Things to Autonomous Systems. We present a new approach as a foundation for remedy against covert channels: while all previous attacks were found by clever thinking of human attackers, this talk presents a formal method called Unique Program Execution Checking which detects and locates vulnerabilities to covert channels systematically, including those to covert channels unknown so far. A detailed report on the presented research results can be found in arXiv:1812.04975, 2018. This is joint work with Mohammad R. Fadiheh (TUK), Dominik Stoffel (TUK), Clark Barrett (Stanford), and Subhasish Mitra (Stanford).

Speaker: Wolfgang Kunz, Technische Universität Kaiserslautern (TUK), Germany

Coffee and cookies will be available.