# FIMBA: Evaluating the Robustness of AI in Genomics via Feature Importance Adversarial Attacks

arXiv: https://arxiv.org/abs/2401.10657 · HTML: https://mlsanity.com/paper/2401.10657/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 45 references that are in the map.
- First posted on arXiv 19 Jan 2024.

## Builds on (most cited first, 12 of 12)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain](https://mlsanity.com/paper/2103.03000/) (2021)
- [A Review of Adversarial Attack and Defense for Classification Methods](https://mlsanity.com/paper/2111.09961/) (2021)
- [LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications](https://mlsanity.com/paper/1910.08536/) (2019)
- [Thwarting Adversarial Examples: An L0-RobustSparse Fourier Transform](https://mlsanity.com/paper/1812.05013/) (2018)

## Built on by (most cited first, 4 of 4)

- [SoK: Security and Privacy Risks of Healthcare AI](https://mlsanity.com/paper/2409.07415/) (2024)
- [GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models](https://mlsanity.com/paper/2505.10983/) (2025)
- [SafeGenes: Evaluating the Adversarial Robustness of Genomic Foundation Models](https://mlsanity.com/paper/2506.00821/) (2025)
- [Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors](https://mlsanity.com/paper/2512.17146/) (2025)

## Abstract (arXiv)

With the steady rise of the use of AI in bio-technical applications and the widespread adoption of genomics sequencing, an increasing amount of AI-based algorithms and tools is entering the research and production stage affecting critical decision-making streams like drug discovery and clinical outcomes. This paper demonstrates the vulnerability of AI models often utilized downstream tasks on recognized public genomics datasets. We undermine model robustness by deploying an attack that focuses on input transformation while mimicking the real data and confusing the model decision-making, ultimately yielding a pronounced deterioration in model performance. Further, we enhance our approach by generating poisoned data using a variational autoencoder-based model. Our empirical findings unequivocally demonstrate a decline in model performance, underscored by diminished accuracy and an upswing in false positives and false negatives. Furthermore, we analyze the resulting adversarial samples via spectral analysis yielding conclusions for countermeasures against such attacks.