DeepSensor: Deep Learning Testing Framework Based on Neuron Sensitivity
- URL: http://arxiv.org/abs/2202.07464v1
- Date: Sat, 12 Feb 2022 16:44:15 GMT
- Title: DeepSensor: Deep Learning Testing Framework Based on Neuron Sensitivity
- Authors: Haibo Jin, Ruoxi Chen, Haibin Zheng, Jinyin Chen, Zhenguang Liu, Qi
Xuan, Yue Yu, Yao Cheng
- Abstract summary: Existing testing methods have provided fine-grained criteria based on neuron coverage and reached high exploratory degree of testing.
To bridge the gap, we observed that neurons which change the activation value dramatically due to minor perturbation are prone to trigger incorrect corner cases.
Motivated by it, we propose neuron sensitivity and develop a novel white-box testing framework for DNN, donated as DeepSensor.
- Score: 20.40306955830653
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite impressive capabilities and outstanding performance, deep neural
network(DNN) has captured increasing public concern for its security problem,
due to frequent occurrence of erroneous behaviors. Therefore, it is necessary
to conduct systematically testing before its deployment to real-world
applications. Existing testing methods have provided fine-grained criteria
based on neuron coverage and reached high exploratory degree of testing. But
there is still a gap between the neuron coverage and model's robustness
evaluation. To bridge the gap, we observed that neurons which change the
activation value dramatically due to minor perturbation are prone to trigger
incorrect corner cases. Motivated by it, we propose neuron sensitivity and
develop a novel white-box testing framework for DNN, donated as DeepSensor. The
number of sensitive neurons is maximized by particle swarm optimization, thus
diverse corner cases could be triggered and neuron coverage be further improved
when compared with baselines. Besides, considerable robustness enhancement can
be reached when adopting testing examples based on neuron sensitivity for
retraining. Extensive experiments implemented on scalable datasets and models
can well demonstrate the testing effectiveness and robustness improvement of
DeepSensor.
Related papers
- Neuroevolutionary algorithms driven by neuron coverage metrics for
semi-supervised classification [60.60571130467197]
In some machine learning applications the availability of labeled instances for supervised classification is limited while unlabeled instances are abundant.
We introduce neuroevolutionary approaches that exploit unlabeled instances by using neuron coverage metrics computed on the neural network architecture encoded by each candidate solution.
arXiv Detail & Related papers (2023-03-05T23:38:44Z) - Can pruning improve certified robustness of neural networks? [106.03070538582222]
We show that neural network pruning can improve empirical robustness of deep neural networks (NNs)
Our experiments show that by appropriately pruning an NN, its certified accuracy can be boosted up to 8.2% under standard training.
We additionally observe the existence of certified lottery tickets that can match both standard and certified robust accuracies of the original dense models.
arXiv Detail & Related papers (2022-06-15T05:48:51Z) - Improving Adversarial Transferability via Neuron Attribution-Based
Attacks [35.02147088207232]
We propose the Neuron-based Attack (NAA), which conducts feature-level attacks with more accurate neuron importance estimations.
We derive an approximation scheme of neuron attribution to tremendously reduce the overhead.
Experiments confirm the superiority of our approach to the state-of-the-art benchmarks.
arXiv Detail & Related papers (2022-03-31T13:47:30Z) - Improving Spiking Neural Network Accuracy Using Time-based Neurons [0.24366811507669117]
Research on neuromorphic computing systems based on low-power spiking neural networks using analog neurons is in the spotlight.
As technology scales down, analog neurons are difficult to scale, and they suffer from reduced voltage headroom/dynamic range and circuit nonlinearities.
This paper first models the nonlinear behavior of existing current-mirror-based voltage-domain neurons designed in a 28nm process, and show SNN inference accuracy can be severely degraded by the effect of neuron's nonlinearity.
We propose a novel neuron, which processes incoming spikes in the time domain and greatly improves the linearity, thereby improving the inference accuracy compared to the
arXiv Detail & Related papers (2022-01-05T00:24:45Z) - Dynamic Neural Diversification: Path to Computationally Sustainable
Neural Networks [68.8204255655161]
Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks.
We explore the diversity of the neurons within the hidden layer during the learning process.
We analyze how the diversity of the neurons affects predictions of the model.
arXiv Detail & Related papers (2021-09-20T15:12:16Z) - The Compact Support Neural Network [6.47243430672461]
We present a neuron generalization that has the standard dot-product-based neuron and the RBF neuron as two extreme cases of a shape parameter.
We show how to avoid difficulties in training a neural network with such neurons, by starting with a trained standard neural network and gradually increasing the shape parameter to the desired value.
arXiv Detail & Related papers (2021-04-01T06:08:09Z) - And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks.
We define AND-like neurons and propose measures to increase their proportion in the network.
Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
arXiv Detail & Related papers (2021-02-15T08:19:05Z) - SeReNe: Sensitivity based Regularization of Neurons for Structured
Sparsity in Neural Networks [13.60023740064471]
SeReNe is a method for learning sparse topologies with a structure.
We define the sensitivity of a neuron as the variation of the network output.
By including the neuron sensitivity in the cost function as a regularization term, we areable to prune neurons with low sensitivity.
arXiv Detail & Related papers (2021-02-07T10:53:30Z) - Artificial Neural Variability for Deep Learning: On Overfitting, Noise
Memorization, and Catastrophic Forgetting [135.0863818867184]
artificial neural variability (ANV) helps artificial neural networks learn some advantages from natural'' neural networks.
ANV plays as an implicit regularizer of the mutual information between the training data and the learned model.
It can effectively relieve overfitting, label noise memorization, and catastrophic forgetting at negligible costs.
arXiv Detail & Related papers (2020-11-12T06:06:33Z) - Non-linear Neurons with Human-like Apical Dendrite Activations [81.18416067005538]
We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy.
We conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing.
arXiv Detail & Related papers (2020-02-02T21:09:39Z) - Investigation and Analysis of Hyper and Hypo neuron pruning to
selectively update neurons during Unsupervised Adaptation [8.845660219190298]
Pruning approaches look for low-salient neurons that are less contributive to a model's decision.
This work investigates if pruning approaches are successful in detecting neurons that are either high-salient (mostly active or hyper) or low-salient (barely active or hypo)
It shows that it may be possible to selectively adapt certain neurons (consisting of the hyper and the hypo neurons) first, followed by a full-network fine tuning.
arXiv Detail & Related papers (2020-01-06T19:46:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.