Biblio

With the widespread deployment of data-driven services, the demand for data volumes continues to grow. At present, many applications lack reliable human supervision in the process of data collection, which makes the collected data contain low-quality data or even malicious data. This low-quality or malicious data make AI systems potentially face much security challenges. One of the main security threats in the training phase of machine learning is data poisoning attacks, which compromise model integrity by contaminating training data to make the resulting model skewed or unusable. This paper reviews the relevant researches on data poisoning attacks in various task environments: first, the classification of attacks is summarized, then the defense methods of data poisoning attacks are sorted out, and finally, the possible research directions in the prospect.

Computer and network accountability is to make every action in computers and networks accountable. In order to achieve accountability, we need to answer the following questions: what did it happen? When did it happen? Who did it? In order to achieve accountability, the first step is to record what exactly happened. Therefore, an accountable logging is needed and implemented in computers and networks. Our previous work proposed a novel accountable logging methodology called Flow-Net. However, how to storage the huge amount of Flow-net logs into databases is not clear. In this paper, we try to answer this question.

Based on our previous work for a novel logging methodology, called flow-net, we propose an Intrusion Detection System (IDS) using Flow-Net Based Fingerprint (IDS-FF) in this paper. We apply the IDS-FF scheme in TCP/IP (Transmission Control Protocol/Internet Protocol) networks for intrusion detection. Experimental results show good performance of the proposed scheme.

Non-Technical Loss (NTL) fraud is a very common fraud in power systems. In traditional power grid, energy theft, via meter tampering, is the main form of NTL fraud. With the rise of Smart Grid, adversaries can take advantage of two-way communication to commit NTL frauds by meter manipulation or network intrusion. Previous schemes were proposed to detect NTL frauds but are not efficient. In this paper, we propose a Fast NTL Fraud Detection and verification scheme (FNFD). FNFD is based on Recursive Least Square (RLS) to model adversary behavior. Experimental results show that FNFD outperforms existing schemes in terms of efficiency and overhead.