Corpus ID: 34561505

Crafting Adversarial Attacks on Recurrent Neural Networks

@inproceedings{Anderson2017CraftingAA,
  title={Crafting Adversarial Attacks on Recurrent Neural Networks},
  author={Mark Anderson and Andrew Bartolo and Pulkit Tandon and tpulkit bartolo},
  year={2017}
}
We developed adversarial input generators to attack a recurrent neural network (RNN) used to classify the sentiment of IMDb movie reviews as being positive or negative. To this end, we developed LSTM network as well as two baseline models SVM and Naı̈ve Bayes and evaluated their accuracy under the attack by two black-box adversaries and a white box adversary. Our results showed that though LSTM is more robust than other two models, it’s still very susceptible to white-box attack with generated… Expand
Vulnerability of Deep Learning Model based Anomaly Detection in Vehicle Network
TLDR
A new optimized method to adopt Long Short Term Memory (LSTM) deep learning model for the ADS in-vehicle network, which leads to an efficient detection system and an efficient Blackbox attack to the adopted ADS using the LSTM model. Expand
Attacks on Machine Learning: Lurking Danger for Accountability
TLDR
It is shown that not all security goals have yet been considered in the literature, either because they were ignored or there are no publications on attacks targeting those goals specifically, and that some are difficult to assess, such as accountability. Expand
Optimized Anomaly Detection System and vulnerability check using black-box attack to vehicle network
---------------------------------------------------------------------***--------------------------------------------------------------------Abstract ECUs are the critical components played criticalExpand

References

SHOWING 1-10 OF 11 REFERENCES
Crafting adversarial input sequences for recurrent neural networks
TLDR
This paper investigates adversarial input sequences for recurrent neural networks processing sequential data and shows that the classes of algorithms introduced previously to craft adversarial samples misclassified by feed-forward neural networks can be adapted to recurrent Neural networks. Expand
Black-Box Attacks against RNN based Malware Detection Algorithms
TLDR
Experimental results showed that RNN based malware detection algorithms fail to detect most of the generated malicious adversarial examples, which means the proposed model is able to effectively bypass the detection algorithms. Expand
Cleverhans V0.1: an Adversarial Machine Learning Library
TLDR
The core functionalities of the cleverhans library are presented, namely the attacks based on adversarial examples and defenses to improve the robustness of machine learning models to these attacks. Expand
Generative Adversarial Networks
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and aExpand
Learning Word Vectors for Sentiment Analysis
TLDR
This work presents a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term--document information as well as rich sentiment content, and finds it out-performs several previously introduced methods for sentiment classification. Expand
Adam: A Method for Stochastic Optimization
TLDR
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Expand
Long Short-Term Memory
TLDR
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Expand
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
TLDR
The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields. Expand
Sentiment Analysis with LSTMs
  • LSTM-Sentiment-Analysis.git,
  • 2017
Backpropagating an LSTM: A Numerical Example. https://blog.aidangomez.ca/2016/04/17/Backpropogating-an-LSTM- A-Numerical-Example
  • 2016
...
1
2
...