LLM Safety Review: Benchmarks & Analysis

On-Demand Webinar

Register now

As more and more applications implement Generative AI, a clear understanding of foundation models' safety risks becomes imperative.

During this webinar, we will review the outcomes of ActiveFence’s LLM safety benchmarking report, which evaluated whether gaps exist in the basic safety of GenAI apps and LLM providers. 

From child exploitation to misinformation, hate speech to self-harm, we will discuss harmful model outputs, the ways bad actors can abuse LLMs, and the risks to those applications that rely on them. 

Join us to learn about how we evaluated LLM safety, and what risks you should consider as you implement these models into your applications.

Speakers

Inbal Goldberger
Inbal Goldberger
VP Trust & Safety
ActiveFence
nitzan
Nitzan Tamari
Generative AI Safety Advisor
ActiveFence
yoni
Yoni Deblinger
VP Extremism
ActiveFence
guy p
Guy Paltieli, PhD
Senior Child Safety Researcher
ActiveFence