DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning
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. Recent works have proposed approximate computation as a defense mechanism against machine learning attacks. We show that...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. Recent works have proposed approximate
computation as a defense mechanism against machine learning attacks. We show
that these approaches, while successful for a range of inputs, are insufficient
to address stronger, high-confidence adversarial attacks. To address this, we
propose DNNSHIELD, a hardware-accelerated defense that adapts the strength of
the response to the confidence of the adversarial input. Our approach relies on
dynamic and random sparsification of the DNN model to achieve inference
approximation efficiently and with fine-grain control over the approximation
error. DNNSHIELD uses the output distribution characteristics of sparsified
inference compared to a dense reference to detect adversarial inputs. We show
an adversarial detection rate of 86% when applied to VGG16 and 88% when applied
to ResNet50, which exceeds the detection rate of the state of the art
approaches, with a much lower overhead. We demonstrate a
software/hardware-accelerated FPGA prototype, which reduces the performance
impact of DNNSHIELD relative to software-only CPU and GPU implementations. |
---|---|
DOI: | 10.48550/arxiv.2208.00498 |