4 papers
Poisoning the corpora of protein design systems during pre-training and retrieval
Charalampos Koilakos, Kimon-Antonios Provatas, Michail Patsakis +3
Protein foundation models increasingly support the generation of novel biological sequences, yet their reliance on large public datasets creates opportunities for adversarial manip…
Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance
Candace S. Y. Chan, Aris Karatzikos, Ilias Georgakopoulos-Soares
Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language models can retrieve and integ…
Structure is not mechanism: high-gain gated-FFN rows across text and genomic foundation models
Alexandros Tzanakakis, Aris Karatzikos, Ilias Georgakopoulos-Soares
A small number of unusually high-gain parameters can exert disproportionate effects in transformer language models, but whether analogous structures recur in genomic foundation mod…
Minimum-Cost Synthetic Genome Planning: An Algorithmic Framework
Michail Patsakis, Ioannis Mouratidis, Ilias Georgakopoulos-Soares
As synthetic genomics scales toward the construction of increasingly larger genomes, computational strategies are needed to address technical feasibility. We introduce an algorithm…