Real-time visibility, safety, and security for your GenAI-powered agents and applications
Proactively test GenAI models, agents, and applications before attackers or users do
Deploy generative AI applications and agents in a safe, secure, and scalable way with guardrails.
Proactively identify vulnerabilities through red teaming to produce safe, secure, and reliable models.
Using the internet, individuals dealing with mental health conditions are able to seek the help and support they need to heal. However, the internet also hosts harmful communities that hurt the health of those who most need help.
ActiveFence investigates online communities promoting self-destructive behaviors around eating disorders. We investigate these communities and provide insights into their means and methods for staying online and the unique vernacular that they have developed. Additionally, we provide a glimpse inside these communities to show how the operate and demonstrate the harmful content they share.