Search Results for author:
Found 5 papers, 1 papers with code
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.
Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attacks
These attacks make small imperceptible modifications to inputs that are sufficient to induce the DNNs to produce the wrong classification.
HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks
This paper presents HASI, a hardware-accelerated defense that uses a process we call stochastic inference to detect adversarial inputs.
Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insights
Further, we have shown the impact of traffic information, time, and points-of-interest data for real-time accident prediction.
RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory
At the same time, the sequential nature of input/weight processing of RNNs mitigates one of the downsides of DWM, which is the linear (rather than constant) data access time. RNNFast is very efficient and highly scalable, with flexible mapping of logical neurons to RNN hardware blocks.
