PRODIGAL

<p>PRODIGAL (proactive discovery of insider threats using graph analysis and learning) is a computer system for predicting anomalous behavior among humans, by <a href="/facts/Data_mining/AH53q5ac">data mining</a> network traffic such as emails, text messages and <a href="/facts/Server_log/p7FHf8mA">server log</a> entries. It is part of <a href="/facts/DARPA/Uf9sarhT">DARPA</a>'s <a href="/facts/Anomaly_Detection_at_Multiple_Scales/24e4AulM">Anomaly Detection at Multiple Scales</a> (ADAMS) project. The initial schedule is for two years and the budget $9 million.
</p><p>It uses <a href="/facts/Graph_theory/VVPCd4TX">graph theory</a>, <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a>, statistical <a href="/facts/Anomaly_detection/wjEGMGGz">anomaly detection</a>, and <a href="/facts/High-performance_computing/HT9NwGAN">high-performance computing</a> to scan larger sets of data more quickly than in past systems. The amount of data analyzed is in the range of <a href="/facts/Terabyte/BNHUp9Qq">terabytes</a> per day. The targets of the analysis are employees within the government or defense contracting organizations; specific examples of behavior the system is intended to detect include the actions of <a href="/facts/Nidal_Malik_Hasan/B6nQ8UK4">Nidal Malik Hasan</a> and <a href="/facts/WikiLeaks/rm4lC2cD">WikiLeaks</a> source <a href="/facts/Chelsea_Manning/Fa9tFdvn">Chelsea Manning</a>. Commercial applications may include finance. The results of the analysis, the five most serious threats per day, go to agents, analysts, and operators working in <a href="/facts/Counterintelligence/MDAxLaSh">counterintelligence</a>.
</p>

PRODIGAL open-in-new

PRODIGAL