2025 – 2026
TheLostKeys
A puzzle-adventure indie game. As founder, I led a remote development team from concept to production, covering strategy, project management and technical direction.
London, UK · MSc AI at King's College London
Giulio
Dajani
A software engineer and AI researcher building tools that help people tell what's real online. Creator of VerifAI, an award-winning multimodal deepfake detector.
84%
First Class Honours, BEng Software Engineering
99.5%
VerifAI balanced accuracy on FakeAVCeleb
4
Countries studied in: Italy, UK, China, South Korea
6
Languages, three of them native
About
Who is Giulio Dajani?
Giulio Dajani is an Italian software engineer and artificial intelligence researcher based in London. He is studying for an MSc in Artificial Intelligence at King's College London, with coursework in deep learning, computer vision and intelligent systems.
He graduated from the University of Greenwich with a First Class BEng (Hons) in Software Engineering. His final-year project, VerifAI, a multimodal deepfake detection framework, received the university's Best Undergraduate Project award.
Alongside his studies, Giulio works as a Technical Support Engineer at Fluent2 Limited in London. He also runs an independent digital products business and founded the indie game studio behind TheLostKeys. Before coming to London he studied Computer Science at the University of Turin. He has also taken part in academic programmes in China and South Korea.
Featured project · 2025–2026
VerifAI
VerifAI is a multimodal deepfake detector. It looks at a video's frames and listens to its audio separately, then combines the two verdicts into one calibrated score. The whole model runs in the browser, so videos never have to leave the user's device.
99.5%balanced accuracy
0.996ROC-AUC
The free demo server may take up to a minute to wake up.
Video framesface crops
Audio trackmel spectrogram
↓
↓
Xceptionvisual branch
ResNet-18audio branch
↘ ↙
Calibrated late fusionper-modality scores, weighted
↓
Real / Fake + confidence
User study · 30 participants
70–80
Most participants' System Usability Scale (SUS) scores fell in the "good usability" range.
Participants used VerifAI to check videos, then rated its usability and how much they trusted it. Most reported moderate to high trust. They preferred seeing a confidence score over a plain real/fake answer.
Tested beyond one dataset
4 benchmark datasets
- FaceForensics++
- Celeb-DF v2
- DeeperForensics
- FakeAVCeleb
Training on several datasets reduced overfitting. The model was also checked on 15 real-world videos it had never seen.
More results
0.999
Average precision
Combining video and audio beat either one alone, and caught mismatches like a real video with fake audio. If a video has no audio, VerifAI switches to a visual-only model automatically.
Why it matters
What the public told us
Findings from the survey run alongside the project.
86%
are concerned deepfakes will be misused for misinformation or fraud
23%
feel highly confident they could spot a deepfake themselves
32%
fully trust AI detection tools, which is why VerifAI shows its confidence
Journey
Turin → London, by way of Asia
🇮🇹 Turin🇬🇧 London🇨🇳 Yancheng🇰🇷 Seoul
Education
2026 – 2027
MSc Artificial Intelligence
King's College London
2026
Communication & Media Studies
Dongguk University, South Korea
2023 – 2026
BEng (Hons) Software Engineering
University of Greenwich, First Class (84%)
2025
Computer Science Summer School
Yancheng Institute of Technology, China
2022 – 2023
Computer Science
University of Turin, Italy
2017 – 2022
Computer Science Diploma
ITIS Technical College, Turin
Experience
2025 – present
Technical Support Engineer
Fluent2 Limited, London
2024 – 2025
Freelance Translator
theEword (remote)
2023
Programmer
Leonardo TEC SNC, Turin
2021
Hardware Technician
SAET S.R.L., Turin
Ventures & projects
Things I've built
2026 – present
Digital products business
An independent business selling digital products on Etsy and Gumroad. I handle product development, branding, marketing and commercial strategy.
2025
AI platform, global team
I worked with students and researchers from several universities to design an AI platform for niche, practical applications.
Toolbox
Skills
Languages
PythonCC#JavaJavaScriptRustGoPHPRubySchemeBashSQL
AI & Web
Deep learningComputer visionONNXFastAPIReactNode.jsASP.NET
Certifications
NDG Linux EssentialsCisco Packet TracerICDLMicrosoft 365
Curriculum vitae
The one-page version
Everything above, condensed onto one page. Download it for recruiters, applications or collaborations.
↓ Download CV (PDF)Contact
Let's talk.
Open to AI research collaborations, internships and interesting problems.
dajani.giulio@gmail.com