no code implementations • 31 Jul 2022 • Mohammad Hossein Samavatian, Saikat Majumdar, Kristin Barber, Radu Teodorescu
DNNs are known to be vulnerable to so-called adversarial attacks that manipulate inputs to cause incorrect results that can be beneficial to an attacker or damaging to the victim.
no code implementations • 20 Jul 2021 • Saikat Majumdar, Mohammad Hossein Samavatian, Kristin Barber, Radu Teodorescu
These attacks make small imperceptible modifications to inputs that are sufficient to induce the DNNs to produce the wrong classification.
no code implementations • 9 Jun 2021 • Mohammad Hossein Samavatian, Saikat Majumdar, Kristin Barber, Radu Teodorescu
This paper presents HASI, a hardware-accelerated defense that uses a process we call stochastic inference to detect adversarial inputs.