Launch agentic AI with confidence. Watch our on-demand webinar to learn how. Watch it Now

About header image

ActiveFence Research

Resources for Trust & Safety and online security professionals

Cover of ActiveFence report titled 'LLM Safety Review: Benchmarks and Analysis' with an illustration of a brain connected to a circuit board.

The LLM Safety Review: Benchmarks & Analysis

Artificial Intelligence, Child Safety, Disinformation, Hate Speech
This first-ever independent benchmarking report into LLM safety provides data-driven insights into the safety of LLMs...
Aug 01, 2023
Read Now
Spain Flag

Spain 2023 Election: What You Need to Know

Disinformation, Election Coverage
Spain's July 23 election marks the start of the EU's 2024 race. ActiveFence shares key insights for Trust & Safety te...
Jun 20, 2023
Read Now
Banner for ActiveFence featuring the text 'Combating Malware Campaigns - The holistic approach to user cyber safety' with illustrations of locks and network connections on a blue background.

Combating Malware Campaigns: The Holistic Approach to User Cyber Safety

Child Safety
ActiveFence shows how emerging malware campaigns can be countered with a proactive, holistic approach combining OSINT...
Jun 19, 2023
Read Now

GenAI: The New Attack Vector for Trust & Safety

Artificial Intelligence
ActiveFence shares exclusive research into how threat actors exploit GenAI to launch new attacks on online safety at ...
May 23, 2023
Read Now
ActiveFence report on 'Child Predator Abuse of Generative AI' with a cover image featuring related visuals.

Child Predator Abuse of Generative AI

Artificial Intelligence, Child Safety
ActiveFence shares exclusive research into how child predators are mapping out GenAI vulnerabilities to create harmfu...
May 23, 2023
Read Now
Crumpled Indian flag with orange, white, and green stripes and blue Ashoka Chakra.

India 2024 Election: Risks in Karnataka State

Disinformation, Election Coverage
ActiveFence shares exclusive research on how to flag emerging online trends that risk social unrest during elections ...
May 09, 2023
Read Now
Person with a bandaged wrist symbolizing self-harm trends and support

Trends in Self-Harm

Child Safety
ActiveFence shares exclusive research into trends within self-harm communities, as they expand and share dangerous co...
Apr 19, 2023
Read Now
Silhouettes of five armed figures holding rifles, set against a blue background with outlines of a cityscape.

Cracking the Terrorist Code

Terrorism
ActiveFence provides exclusive intelligence showing how to detect the hidden online activity of terrorists by underst...
Mar 15, 2023
Read Now
ActiveFence State of Trust & Safety 2023 report cover with the tagline 'Proactively Countering Online Harm' on a blue background

The State of Trust & Safety 2023

The State of Trust & Safety 2023 report provides key intelligence insights on shifts in political disinformation, ter...
Feb 15, 2023
Read Now

Categories

Latest Posts

Red Teaming GenAI NPCs: 5 Principles for Safer, Smarter AI Companions in Gaming
Red Teaming GenAI NPCs: 5 Principles for Safer, Smarter AI Companions in Gaming
Discover how bad actors misuse GenAI
Synthetic Lies, Real Victims
Executive Insights: Navigating Strategic Challenges in GenAI Deployment
Bridging Frameworks to Function in AI Safety and Security – A Practical Guide
Misleading Models – Testing for Deception
1 … 3 4 5 6 7 … 10