Retraining Deep Neural Network with Unlabeled Data Collected in Embedded Devices

Because of computational complexity,the deep neural network(DNN)in embedded devices is usually trained on high-performance computers or graphic processing units(GPUs),and only the inference phase is implemented in embedded devices.Data processed by embedded devices,such as smartphones and wearables,are usually personalized,so the DNN model trained on public data sets may have poor accuracy when inferring the personalized data.As a result,retraining DNN with personalized data collected locally in embedded devices is necessary.Nevertheless,retraining needs labeled data sets,while the data collected locally are unlabeled,then how to retrain DNN with unlabeled data is a problem to be solved.This paper proves the necessity of retraining DNN model with personalized data collected in embedded devices after trained with public data sets.It also proposes a label generation method by which a fake label is generated for each unlabeled training case according to users’feedback,thus retraining can be performed with unlabeled data collected in embedded devices.The experimental results show that our fake label generation method has both good training effects and wide applicability.The advanced neural networks can be trained with unlabeled data from embedded devices and the individualized accuracy of the DNN model can be gradually improved along with personal using.

Study on a clamping device of leveling equipment mounted on jacket

This paper proposes a novel clamping device for leveling equipment mounted on offshore oil platform jacket,which solves the problem of leveling equipment clamping lifting force of more than 2000 tons.The main features are that lifting force transmits to clamp claw through wedge force amplifier,embed the teeth of claw into the pile,and the embedded depth increases with the lifting force,resulting in a gravitational self-locking function.This theoretical model of clamping device was established,and the force and material characteristic were analyzed,and the feasibility of the theoretical model was verified by thin shell elastic-plastic stability theory and thin-walled structures theory.An experimental prototype of clamping device was produced to test gravity self-locking function and bearable leveling force.Compared with the theoretical model and the experimental results,it proved that the embedded clamping devices have gravitational self-locking function and can meet the need of actual leveling equipment.

FirmVulSeeker—BERT and Siamese Network-Based Vulnerability Search for Embedded Device Firmware Images

In recent years,with the development of the natural language processing(NLP)technologies,security analyst began to use NLP directly on assembly codes which were disassembled from binary executables in order to examine binary similarity,achieved great progress.However,we found that the existing frameworks often ignored the complex internal structure of instructions and didn’t fully consider the long-term dependencies of instructions.In this paper,we propose firmVulSeeker—a vulnerability search tool for embedded firmware images,based on BERT and Siamese network.It first builds a BERT MLM task to observe and learn the semantics of different instructions in their context in a very large unlabeled binary corpus.Then,a finetune mode based on Siamese network is constructed to guide training and matching semantically similar functions using the knowledge learned from the first stage.Finally,it will use a function embedding generated from the fine-tuned model to search in the targeted corpus and find the most similar function which will be confirmed whether it’s a real vulnerability manually.We evaluate the accuracy,robustness,scalability and vulnerability search capability of firmVulSeeker.Results show that it can greatly improve the accuracy of matching semantically similar functions,and can successfully find more real vulnerabilities in real-world firmware than other tools.

Saving Environment Using Internet of Things: Challenges and the Possibilities

The term Internet of Things (IoT) emerged in the early 2000s but actually gained momentum only in the past few years, however we still do not get to see them in our daily life. It has generally been avoided by the mainstream market due to its “cryptic” nature which requires technical knowledge prior to its use. Lack of strong business model (by companies) and inability to adapt to new rapid changes (by consumers) are the two primary factors contributing to the fact that IoT is well ahead of its times but it need no longer be. In this paper, I’ve created a setup for smart home that allows the users to control their electrical appliances from internet and even makes the appliances smart enough to react to the environmental conditions on their own. Using this setup, I observed the pattern in which electricity consumption and carbon footprints reduced as compared to the conventional setup i.e. without IoT. Analyzing this data provided me a solid proof that IoT definitely helps us to save electricity and environment. Since IoT is beneficial for all, I, then focused on the challenges that are hampering the penetration of IoT into the daily lives of consumers and how the consumer is overlooking the benefits that it has to offer, which even includes a primary concern for many, i.e. saving money. This paper is overall aimed to change the way a consumer thinks about IoT and to provide a solid ground to how it is beneficial.