SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing
Directed fuzzing steers fuzzers toward user-defined sink functions to identify vulnerabilities, but it frequently fails to trigger crashes even after long campaigns. We identify two challenges that prevent directed fuzzers from exposing cra
https://arxiv.org/abs/2607.08949v2 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
llm, 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
J
Junmin Zhu
1.0
low confidence
S
Siyu Liu
1.0
low confidence
J
Jie Hu
1.0
low confidence
F
Fabio Gritti
1.0
low confidence
A
Ati Priya Bajaj
1.0
low confidence
H
Hulin Wang
1.0
low confidence
W
Wenbo Guo
1.0
low confidence
T
Tiffany Bao
1.0
low confidence
C
Christopher Kruegel
1.0
low confidence
G
Giovanni Vigna
1.0
low confidence
Sabera Hussain
Everest Munro-Zeisberger
Andrei Serban
Bjoern Zinssmeister