High Performance Computing Cluster for NLP and Deep Learning Approaches to Understanding Social, Psychological, and Rhetorical Dimensions of Influence in Cross-Cultural Contexts

High Performance Computing Cluster for NLP and Deep Learning Approaches to Understanding Social, Psychological, and Rhetorical Dimensions of Influence in Cross-Cultural Contexts High Performance Computing Cluster for NLP and Deep Learning Approaches to Understanding Social, Psychological, and Rhetorical Dimensions of Influence in Cross-Cultural Contexts In the 21st century security environment, the information domain has become a primary arena of both nation-state and non-state actor conflict. Populations are influenced, democracies disrupted, and human behaviors shaped through manipulations of information and exploitation of the channels through which information flows. Military services and their information operations and intelligence directorates need faster and more accurate insights into how the range of disinformation and influence techniques an adversary brings to bear can influence a population, from deep-fakes to adversarial framing to botnets and troll farms. A common characteristic of investigations into disinformation techniques and technologies is a need for high performance computing to process massive amounts of data, run generative networks, and train deep learning models. In order to support multidisciplinary, DOD-funded research into disinformation, information conflict, and influence currently underway at Arizona State University (ASU), we propose to acquire a five-node, high performance computing system. Each node will include the necessary memory, CPU power, and GPU power to efficiently run Natural Language Processing tasks, such as training of language models or generation of synthetic data for development of detection and attribution algorithms. Each node will include a CPU module with AMD processors with 64 cores, 512GB RAM, and four 40GB A100 NVIDIA GPUs. The proposed equipment will expand research capabilities for several existing DOD-funded research projects at ASU, and will enable new opportunities for DOD research in a variety of disciplines. The fivenode array will allow for efficient computation of especially large tasks, and more importantly enable the simultaneous execution of multiple tasks supporting the multiple research efforts engaged in: Development of new capabilities for information environment assessment in dynamic information contests New technologies for detecting social hysteria propagation, crowd manipulation and group polarization processes Cyber conflict resolution and understanding the problem of influence, socially, psychologically and cross-culturally To robustly answer questions about how to rapidly attribute synthetically-generated deceptive media artifacts to nefarious actors, how to accurately identify and characterize and counter crosscultural vectors of influence, and how to detect propaganda and disinformation using unsupervised machine learning, multidisciplinary collaboration is required between psychologists, anthropologists, communication scholars, media scholars, as well as computer scientists, data mining experts, and data visualization specialists. At ASU, these collaborations are ongoing and facilitated by the Center on Narrative, Disinformation, and Strategic Influence (NDSI, directed by PI Ruston) in collaboration with the Center for Strategic Communication (CSC, directed by Co-PI Corman) and the Data Mining and Machine Learning Lab (DMML, directed by Co-PI Liu). These three research organizations have five projects currently underway engaged in detection, attribution, and characterization of disinformation and/or covert online influence in different cultural contexts. Additionally, NDSI sponsors ASUs Disinformation Working Group, assembling approximately 20 scholars from across the university to engage with mission-relevant research supporting the research areas articulated above.