Online Social Networks (OSN) are becoming the de facto communication medium around the world. As people move away from traditional voice communications for texting and instant messaging, we are also seeing a shift in how people get their news. More and more people are turning to OSNs to get information instead of the more traditional news sources (e.g., television, print and radio).
As these companies are becoming more influential, they are also facing numerous threats that can affect the integrity and quality of the experience for stakeholders within the content ecosystem. It is increasingly important that the OSN ensures all possible controls are in place to protect the integrity of their information. These controls include continuously updating their threat model, interrogating its data and developing countermeasures to adversarial activity– all of which serve to maintain stakeholder trust. Failure to implement these measures may result in fraud or manipulation of the digital content cultivated within the ecosystem. That failure represents a significant risk to the OSN and necessitates an innovative approach to facilitate the machine-based search and automated interdiction of threat actors within the ecosystem.
Traditional methods to detect and defend against adversarial activity on OSNs have relied on the identification of static indicators of compromise and time-consuming, manual investigations to determine if an event is malicious. These fragmented approaches to detection traditionally address threats in isolation and fail to incorporate information available to the OSN in a holistic and meaningful way. The creation of a counter threat fusion cell to coordinate and focus threat collection, analysis and subsequent interdiction efforts within the ecosystem would allow OSNs to better predict threats and quickly respond to attempts to sabotage the integrity of their content, ultimately impacting the relationship between the OSN and their users.