| Title | Poisoning Attack on Show and Tell Model and Defense Using Autoencoder in Electric Factory |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Lee, Dongseop, Kim, Hyunjin, Ryou, Jaecheol |
| Conference Name | 2020 IEEE International Conference on Big Data and Smart Computing (BigComp) |
| Keywords | AI, AI Poisoning, autoencoder, Data models, defense, Dogs, Human Behavior, image recognition, image restoration, Neural networks, poisoning attack, pubcrawl, Resiliency, Scalability, show and tell model, Toxicology, Training data |
| Abstract | Recently, deep neural network technology has been developed and used in various fields. The image recognition model can be used for automatic safety checks at the electric factory. However, as the deep neural network develops, the importance of security increases. A poisoning attack is one of security problems. It is an attack that breaks down by entering malicious data into the training data set of the model. This paper generates adversarial data that modulates feature values to different targets by manipulating less RGB values. Then, poisoning attacks in one of the image recognition models, the show and tell model. Then use autoencoder to defend adversarial data. |
| DOI | 10.1109/BigComp48618.2020.000-9 |
| Citation Key | lee_poisoning_2020 |
Poisoning Attack on Show and Tell Model and Defense Using Autoencoder in Electric Factory