Search papers, labs, and topics across Lattice.
This paper introduces a multi-vector privacy evaluation framework to quantify memorization risks in Genomic Language Models (GLMs) using perplexity-based detection, canary sequence extraction, and membership inference. The framework is used to evaluate memorization across different GLM architectures and training regimes, revealing measurable memorization that varies based on architecture and training. The study highlights the necessity of multi-vector privacy auditing for genomic AI systems, as no single attack vector fully captures the scope of memorization risk.
Genomic language models memorize training data, raising privacy concerns, and this study shows that no single memorization attack can fully capture the risk, necessitating a multi-vector approach to auditing.
Genomic language models (GLMs) have emerged as powerful tools for learning representations of DNA sequences, enabling advances in variant prediction, regulatory element identification, and cross-task transfer learning. However, as these models are increasingly trained or fine-tuned on sensitive genomic cohorts, they risk memorizing specific sequences from their training data, raising serious concerns around privacy, data leakage, and regulatory compliance. Despite growing awareness of memorization risks in general-purpose language models, little systematic evaluation exists for these risks in the genomic domain, where data exhibit unique properties such as a fixed nucleotide alphabet, strong biological structure, and individual identifiability. We present a comprehensive, multi-vector privacy evaluation framework designed to quantify memorization risks in GLMs. Our approach integrates three complementary risk assessment methodologies: perplexity-based detection, canary sequence extraction, and membership inference. These are combined into a unified evaluation pipeline that produces a worst-case memorization risk score. To enable controlled evaluation, we plant canary sequences at varying repetition rates into both synthetic and real genomic datasets, allowing precise quantification of how repetition and training dynamics influence memorization. We evaluate our framework across multiple GLM architectures, examining the relationship between sequence repetition, model capacity, and memorization risk. Our results establish that GLMs exhibit measurable memorization and that the degree of memorization varies across architectures and training regimes. These findings reveal that no single attack vector captures the full scope of memorization risk, underscoring the need for multi-vector privacy auditing as a standard practice for genomic AI systems.
