As GenAI tools and the LLMs behind them impact the daily lives of billions, this report examines whether these technologies can be trusted to keep users safe.
What you’ll learn:
- How LLMs respond to risky prompts from bad actors and vulnerable users
- Where current models show safety strengths and weaknesses
- Actionable steps to improve LLM safety and reduce harmful outcomes
Overview
In this first independent benchmarking report on the LLM safety landscape, ActiveFence’s subject-matter experts put leading models to the test. More than 20,000 prompts were used to analyze how six LLMs respond across seven major languages and four high-risk abuse areas: child exploitation, hate speech, self-harm, and misinformation. The report provides comparative insight into each model’s relative safety strengths and weaknesses, helping teams understand where gaps exist and where additional resources may be required.
What’s New from Alice
Curiouser Soundbites: What a Former Google Cloud CISO Wants Leaders to Know About AI
Everyone's watching the flood of new AI vulnerabilities. Former Google Cloud CISO Phil Venables is watching something else, and it's the shift leaders can't afford to miss.
AI in Healthcare: Protecting Patient Data Without Falling Behind
Your doctor knows things about you that almost nobody else does. So what happens when AI gets access to all of it? Sandy Dunn has spent much of her career worrying about exactly that. She's a healthcare CISO, and her answer is calmer than you'd think: the things that can go wrong aren't new, it's how fast they happen and how far the damage spreads. In this episode, she and Mo get into why HIPAA has become paperwork that protects almost nobody, why the safest data is the data you never collected, and what happens to trust when AI is in the exam room.
It Takes AI to Break AI: The Case for AI Red Teaming
As AI systems gain autonomy, organizations need security approaches built specifically for AI behavior. Learn why AI-driven red teaming is becoming a critical defense layer.
Demystifying AI Red Teaming
Your AI passed every check. That doesn't mean it's safe. Learn how to red team AI systems before adversaries find the gaps you missed.
