FIMBA: Evaluating the Robustness of AI in Genomics via Feature
Importance Adversarial Attacks
- URL: http://arxiv.org/abs/2401.10657v1
- Date: Fri, 19 Jan 2024 12:04:31 GMT
- Title: FIMBA: Evaluating the Robustness of AI in Genomics via Feature
Importance Adversarial Attacks
- Authors: Heorhii Skovorodnikov, Hoda Alkhzaimi
- Abstract summary: 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.
Our empirical findings unequivocally demonstrate a decline in model performance, underscored by diminished accuracy and an upswing in false positives and false negatives.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Machine Learning for ALSFRS-R Score Prediction: Making Sense of the Sensor Data [44.99833362998488]
Amyotrophic Lateral Sclerosis (ALS) is a rapidly progressive neurodegenerative disease that presents individuals with limited treatment options.
The present investigation, spearheaded by the iDPP@CLEF 2024 challenge, focuses on utilizing sensor-derived data obtained through an app.
arXiv Detail & Related papers (2024-07-10T19:17:23Z) - Adjoint Sensitivity Analysis on Multi-Scale Bioprocess Stochastic Reaction Network [2.6130735302655554]
We introduce an adjoint sensitivity approach to expedite the learning of mechanistic model parameters.
In this paper, we consider enzymatic analysis (SA) representing a multi-scale bioprocess mechanistic model.
arXiv Detail & Related papers (2024-05-07T05:06:45Z) - Unmasking Dementia Detection by Masking Input Gradients: A JSM Approach
to Model Interpretability and Precision [1.5501208213584152]
We introduce an interpretable, multimodal model for Alzheimer's disease (AD) classification over its multi-stage progression, incorporating Jacobian Saliency Map (JSM) as a modality-agnostic tool.
Our evaluation including ablation study manifests the efficacy of using JSM for model debug and interpretation, while significantly enhancing model accuracy as well.
arXiv Detail & Related papers (2024-02-25T06:53:35Z) - Model Stealing Attack against Graph Classification with Authenticity,
Uncertainty and Diversity [85.1927483219819]
GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions.
We introduce three model stealing attacks to adapt to different actual scenarios.
arXiv Detail & Related papers (2023-12-18T05:42:31Z) - QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement.
QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights.
We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
arXiv Detail & Related papers (2023-11-06T00:21:44Z) - MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data
Augmentation [58.93221876843639]
This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion.
It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space.
It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
arXiv Detail & Related papers (2023-10-04T01:36:30Z) - Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue
Response Generation Models by Causal Discovery [52.95935278819512]
We conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work.
Inspired by causal discovery algorithms, we propose a novel model-agnostic method for training and inference of response generation model.
arXiv Detail & Related papers (2023-03-02T06:33:48Z) - Estimating productivity gains in digital automation [0.0]
This paper proposes a novel productivity estimation model to evaluate the effects of adopting Artificial Intelligence (AI) components in a production chain.
We provide (i) theoretical and empirical evidence to explain Solow's dichotomy; (ii) a data-driven model to estimate and asses productivity variations; (iii) a methodology underpinned on process mining datasets to determine the business process, BP, and productivity.
arXiv Detail & Related papers (2022-10-03T22:11:42Z) - CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal
Relationships [8.679073301435265]
We construct a new benchmark for evaluating and improving model robustness by applying perturbations to existing data.
We use these labels to perturb the data by deleting non-causal agents from the scene.
Under non-causal perturbations, we observe a $25$-$38%$ relative change in minADE as compared to the original.
arXiv Detail & Related papers (2022-07-07T21:28:23Z) - Improving robustness of jet tagging algorithms with adversarial training [56.79800815519762]
We investigate the vulnerability of flavor tagging algorithms via application of adversarial attacks.
We present an adversarial training strategy that mitigates the impact of such simulated attacks.
arXiv Detail & Related papers (2022-03-25T19:57:19Z) - Adversarial Sample Enhanced Domain Adaptation: A Case Study on
Predictive Modeling with Electronic Health Records [57.75125067744978]
We propose a data augmentation method to facilitate domain adaptation.
adversarially generated samples are used during domain adaptation.
Results confirm the effectiveness of our method and the generality on different tasks.
arXiv Detail & Related papers (2021-01-13T03:20:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.