Apr 27, 2026
PROJECT MOSAIC: Defensive Protein-Aware Screening for Benchtop Synthesizers
Abubakar Abdulfatah
Project MOSAIC provides an open-source, Protein-Aware Mock Screener tool designed to defend against "context-scrubbed" multi-agent LLM workflows.
We demonstrate that while simple DNA-level screening (Hamming distance) can be trivially evaded by generating synonymous codon substitutions using commercial LLMs (yielding 3 unique evasion payloads across 9 tested trials), our Layer-2 Protein Translation Screener catches 100% of these adversarial payloads by examining the translated amino acid homology, providing a robust defense against synonymous-only substitutions.
This project explicitly models how malicious users might split a dangerous request into benign subtasks across different models, and provides the defensive code necessary to catch the resulting obfuscated sequences before they reach physical synthesis.
I appreciated an attempt at a red-teaming pipeline and found the paper relatively clear to read. The use of multiple models in its pipeline was also appreciated.
However, the obfuscation techniques and screening strategies proposed are not novel compared to state-of-the-art screening tools. In addition, while the paper proposes defensive screening for benchtop synthesizers, the bulk of the paper focuses on its red-teaming and screening strategies and not enough on implementation methods specifically into benchtop synthesizers. I would either hone in on that implementation or on novel red-teaming and stress testing strategies that can be done, building on methods used by current screening tools.
It’s an interesting project that encompasses red teaming, tool development, and policy recommendations. The “multi-agent context-scrubbing” attack seems to be clearly described. The end-to-end approach here is very good, in that it starts with a vulnerability, exploits it, defends against it, and ties it back to policy. Empirically, the project has good design that includes the control group and uses cross-model testing on several frontier models. Defensively, it gives an applied screening argument which is further improved by using an open-source protein-level screen. Policy-wise, it talks about the risks of benchtop synthesizers which are highly relevant and one of the main bottlenecks of DNA synthesis screening, and the project presents somewhat useful policy guidance on this topic.
Where it could be stronger: Novelty varies, where the biological principle that screening at the protein level works better than screening at the DNA level is common knowledge in industry and the use of HMMs in screening (commec uses it). While the project sometimes overstates the novelty of the work, claims such as "absolute mathematical guarantee" are quite hyperbolic, considering the authors' admission of non-synonymous evasions and structure-preserving mutations. The experiments are constrained by the choice of a benign sample (GFP), lack a test on more recent synthesis companies, modern screening pipelines, or even more sophisticated attacks.
Cite this work
@misc {
title={
(HckPrj) PROJECT MOSAIC: Defensive Protein-Aware Screening for Benchtop Synthesizers
},
author={
Abubakar Abdulfatah
},
date={
4/27/26
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}
