Context-Aware Destination and Time-To-Destination Prediction Using Machine learning
More Like this
-
Abstract Prior approaches to AS-aware path selection in Tor do not consider node bandwidth or the other characteristics that Tor uses to ensure load balancing and quality of service. Further, since the AS path from the client’s exit to her destination can only be inferred once the destination is known, the prior approaches may have problems constructing circuits in advance, which is important for Tor performance. In this paper, we propose and evaluate DeNASA, a new approach to AS-aware path selection that is destination-naive, in that it does not need to know the client’s destination to pick paths, and that takes advantage of Tor’s circuit selection algorithm. To this end, we first identify the most probable ASes to be traversed by Tor streams. We call this set of ASes the Suspect AS list and find that it consists of eight highest ranking Tier 1 ASes. Then, we test the accuracy of Qiu and Gao AS-level path inference on identifying the presence of these ASes in the path, and we show that inference accuracy is 90%. We develop an AS-aware algorithm called DeNASA that uses Qiu and Gao inference to avoid Suspect ASes. DeNASA reduces Tor stream vulnerability by 74%. We also show that DeNASA has performance similar to Tor. Due to the destination-naive property, time to first byte (TTFB) is close to Tor’s, and due to leveraging Tor’s bandwidth-weighted relay selection, time to last byte (TTLB) is also similar to Tor’s.more » « less
-
Abstract Over the last few years, understanding of the effects of increasingly interconnected global flows of agricultural commodities on coupled human and natural systems has significantly improved. However, many important factors in environmental change that are influenced by these commodity flows are still not well understood. Here, we present an empirical spatial modelling approach to assess how changes in forest cover are influenced by trade destination. Using data for soybean-producing municipalities in the state of Mato Grosso, Brazil, between 2004 and 2017, we evaluated the relationships between forest cover change and the annual soybean trade destination. Results show that although most of the soybean produced in Mato Grosso during the study period (60%) was destined for international markets, municipalities with greater and more consistent soybean production not destined for international markets during the study period were more strongly associated with deforestation. In these municipalities, soybean production was also significantly correlated with cattle and pasture expansion. These results have important implications for the sustainable management of natural resources in the face of an increasingly interconnected world, while also helping to identify the most suitable locations for implementing policies to reduce deforestation risks.more » « less
An official website of the United States government

