NewThe detectors that scored perfect collapsed the hardest under attack.
Blog and publications

The library.

Everything we publish in one place: white papers, articles, and short notes. Search by keyword or filter by topic and format.

6 entries in the library
Benchmarks1Methodology notes2Threat briefings1Explainers1Fraud stories1

6 results

June 2026
BenchmarksWhite paper

Detectors collapse from near-perfect to near-random.

An initial benchmark and robustness re-evaluation of leading open-source deepfake detectors, stratified across generators, platform degradations, and demographic groups.

Read6 min read
Upcoming
Methodology notesNote

Why an AUC near 1.0 is usually a confound, not a result.

When a detector scores almost perfectly on a single dataset, the likeliest explanation is that it learned the dataset, not the attack.

Coming soon
Upcoming
Methodology notesNote

Report the worst group, not the average.

Why a pooled accuracy number hides the subgroup failures that matter most for fraud and fairness.

Coming soon
Upcoming
Threat briefingsArticle

The deepfake-hiring pipeline, and what detectors miss.

How synthetic candidates clear interviews, and where the detection layer tends to break.

Coming soon
Upcoming
ExplainersArticle

What a detector sees, and why compression fools it.

A plain-language look at how platform re-encoding erases the very artifacts a detector relies on.

Coming soon
Upcoming
Fraud storiesArticle

How a deepfake cleared a live video identity check.

A walkthrough of a synthetic-media fraud pattern and the verification gap that let it through.

Coming soon

Field notes

Quarterly changes in attacker tooling, in your inbox.

A short briefing on shifts in attacker tooling, four times a year.

Research and benchmarks only. Unsubscribe anytime.