DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning

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.

BIG-bench Machine Learning

Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attacks

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.

Autonomous Vehicles BIG-bench Machine Learning

HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks

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.

BIG-bench Machine Learning