The ActiveFence Engineering Blog

Why is it difficult to receive feedback (even for AI)

Labeled datasets are invaluable assets. There is a direct link between dataset quality and model performance. Efficient, robust, and sensitive harmful content detection leverages numerous supervised models, so it is critical for us to have funnels that generate useful labels and make the most out of them.

Iddo Aviram
Feb 28, 2023
7 min read
How Fingerprints Fight Online Evil

How Fingerprints Fight Online Evil

Malicious content, including hate speech, misinformation, and CSAM are readily shared on social media platforms. However, using technology, we can make the work of resharing that content more difficult.

Ziv Kalderon
Mar 28, 2023
5 min read
Racism, Hate, and Weddings- 3 Ways to Avoid Biased Data

Racism, Hate, and Weddings- 3 Ways to Avoid Biased Data

Working with biased data presents many problems. Here, we share how to diagnose, handle, and reduce such data

Maya Raifer
Jan 17, 2022
7 min read
Constructing and querying a data model for online harm- Part 1

Constructing and querying a data model for online harm- Part 1

Online content, media creators, and user interactions must be captured to build algorithms that detect harmful activity. Here, we discuss the data model that captures the complexities of this online ecosystem and how we use it to detect malicious activity at scale

Matar Haller
Jan 11, 2023
3 min read
Constructing and querying a data model for online harm  – Part 2

Constructing and querying a data model for online harm – Part 2

Online content, media creators, and user interactions must be captured to build algorithms that detect harmful activity. Here, we discuss the data model that captures the complexities of this online ecosystem and how we use it to detect malicious activity at scale

Noam Levy
Jan 11, 2023
8 min read
The Metaverse: Helping Platforms Keep Us Safe in New Digital Territory

The Metaverse: Helping Platforms Keep Us Safe in New Digital Territory

The metaverse presents a unique opportunity to foster community and drive innovation online. However, it also opens the door for a greater risk of harm, which is more difficult to detect and proactively combat. However, with contextual AI, safety in the metaverse stands a chance

Matar Haller
Dec 30, 2022
5 min read
ActiveFence R&D on Practical AI Podcast

ActiveFence R&D on Practical AI Podcast

Listen to how we build AI that solves the complex challenges of content moderation on this podcast with Matar Haller, Daniel Whitenack & Chris Benson

Matar Haller
Jan 17, 2023
1 min read