Search Results for author: Saad Islam

Found 4 papers, 2 papers with code

Don't Knock! Rowhammer at the Backdoor of DNN Models

1 code implementation14 Oct 2021 M. Caner Tol, Saad Islam, Andrew J. Adiletta, Berk Sunar, Ziming Zhang

To this end, we first investigate the viability of backdoor injection attacks in real-life deployments of DNNs on hardware and address such practical issues in hardware implementation from a novel optimization perspective.

An Optimization Perspective on Realizing Backdoor Injection Attacks on Deep Neural Networks in Hardware

no code implementations29 Sep 2021 M. Caner Tol, Saad Islam, Berk Sunar, Ziming Zhang

Recent works focus on software simulation of backdoor injection during the inference phase by modifying network weights, which we find often unrealistic in practice due to the hardware restriction such as bit allocation in memory.

SPOILER: Speculative Load Hazards Boost Rowhammer and Cache Attacks

3 code implementations1 Mar 2019 Saad Islam, Ahmad Moghimi, Ida Bruhns, Moritz Krebbel, Berk Gulmezoglu, Thomas Eisenbarth, Berk Sunar

We propose the SPOILER attack which exploits this leakage to speed up this reverse engineering by a factor of 256.

Cryptography and Security

Undermining User Privacy on Mobile Devices Using AI

no code implementations27 Nov 2018 Berk Gulmezoglu, Andreas Zankl, M. Caner Tol, Saad Islam, Thomas Eisenbarth, Berk Sunar

Over the past years, literature has shown that attacks exploiting the microarchitecture of modern processors pose a serious threat to the privacy of mobile phone users.

Cannot find the paper you are looking for? You can Submit a new open access paper.