Search Results for author:
Found 7 papers, 0 papers with code
Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning
Data augmentation is widely used to mitigate data bias in the training dataset.
Revealing CNN Architectures via Side-Channel Analysis in Dataflow-based Inference Accelerators
The proposed attack exploits spatial and temporal data reuse of the dataflow mapping on CNN accelerators and architectural hints to recover the structure of CNN models.
Breaking On-Chip Communication Anonymity using Flow Correlation Attacks
We show that the existing anonymous routing is vulnerable to machine learning (ML) based flow correlation attacks on NoCs.
Hardware Acceleration of Explainable Artificial Intelligence
Extensive experimental evaluation demonstrates that proposed approach deployed on TPU can provide drastic improvement in interpretation time (39x on average) as well as energy efficiency (69x on average) compared to existing acceleration techniques.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Backdoor Attacks on Bayesian Neural Networks using Reverse Distribution
In this paper, we propose a novel backdoor attack based on effective learning and targeted utilization of reverse distribution.
Fast Approximate Spectral Normalization for Robust Deep Neural Networks
One promising strategy to counter adversarial attacks is to utilize spectral normalization, which ensures that the trained model has low sensitivity towards the disturbance of input samples.
Hardware Acceleration of Explainable Machine Learning using Tensor Processing Units
(1) To the best of our knowledge, our proposed work is the first attempt in enabling hardware acceleration of explainable ML using TPUs.
