After some incredibly annoying stalled research, I am close to empirically demonstrating that the #neuralnets used for machine learning-assisted software vulnerability detection #mlavd are *only* recognizing code patterns and not able to perform the calculations and code-flow required to test for vulnerability.

#warning These are early, tentative results. Still working on testing the graph and transformer-based models. I do expect graph models to perform somewhat better, but we'll see.

#Introduction I'm a PhD student at Wright State, MS from USC #GoTrojans. My research is on establishing the fundamentals of ML-assisted software vulnerability detection #MLAVD.

Q's like:
- What are the best datasets we have?
- What models are capable of the performing SVD?

I also work on #AIEthics for highly-regulated model deployments - e.g., governments. I'm the originator of "Prediction Facts" which applies previous work from the dataset and model level to individual predictions.

#SayHi