GeoDetect: Geometric Adversarial Detection for VLPs
Vision-language pre-trained models (VLPs) are widely used in real-world applications. However, they remain vulnerable to adversarial attacks. Although adversarial detection methods have demonstrated success in single-modality settings (eith
https://arxiv.org/abs/2607.14737v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
None
How close the company’s idea is to your thesis statement
Sector
ai
Overlap with sectors you care about
Geography
Unknown
Location unknown — scores 0
Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”
Founder → stable
Traction → stable
Idea vs market ↑ improving
▸ Add / edit details
Correct facts used on the next screening or memo.
People
A
Afsaneh Hasanebrahimi
1.0
low confidence
H
Hanxun Huang
1.0
low confidence
C
Christopher Leckie
1.0
low confidence
J
James Bailey
1.0
low confidence
S
Sarah Erfani
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
SubVysion
· Active
We help contractors dig safer with 3D maps of underground…
founders not scraped yet
Segments.ai
· Acquired
Build better computer vision models by building better datasets
Otto Debals
Bert De Brabandere
RunLocal AI
· Active
The AI agent for model deployment, inference optimization and…
founders not scraped yet
Protex AI
· Active
Computer vision that makes the industrial workplace, safer
founders not scraped yet
Mark Stauber
Jaeyong Sung