Hidden in Plain Sight: Undetectable Adversarial Bias Attacks on Vulnerable Patient Populations

• URL: http://arxiv.org/abs/2402.05713v3
• Date: Sun, 7 Apr 2024 16:59:41 GMT
• Title: Hidden in Plain Sight: Undetectable Adversarial Bias Attacks on Vulnerable Patient Populations
• Authors: Pranav Kulkarni, Andrew Chan, Nithya Navarathna, Skylar Chan, Paul H. Yi, Vishwa S. Parekh,
• Abstract summary: We show that demographically targeted label poisoning attacks can introduce undetectable underdiagnosis bias in deep learning (DL) models. Our results indicate that adversarial bias attacks result in biased DL models that propagate prediction bias even when evaluated with external datasets.
• Score: 3.5984704795350315
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The proliferation of artificial intelligence (AI) in radiology has shed light on the risk of deep learning (DL) models exacerbating clinical biases towards vulnerable patient populations. While prior literature has focused on quantifying biases exhibited by trained DL models, demographically targeted adversarial bias attacks on DL models and its implication in the clinical environment remains an underexplored field of research in medical imaging. In this work, we demonstrate that demographically targeted label poisoning attacks can introduce undetectable underdiagnosis bias in DL models. Our results across multiple performance metrics and demographic groups like sex, age, and their intersectional subgroups show that adversarial bias attacks demonstrate high-selectivity for bias in the targeted group by degrading group model performance without impacting overall model performance. Furthermore, our results indicate that adversarial bias attacks result in biased DL models that propagate prediction bias even when evaluated with external datasets.

Related papers

• How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
  This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs. Our findings reveal that biases present in pre-training data are amplified in model outputs.
  arXiv  Detail & Related papers  (2024-11-28T16:20:25Z)
• Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI [17.101569078791492]
  We study 43 CLIP vision-language models to determine whether they learn human-like facial impression biases. We show for the first time that the the degree to which a bias is shared across a society predicts the degree to which it is reflected in a CLIP model.
  arXiv  Detail & Related papers  (2024-08-04T08:26:58Z)
• Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias [3.455189439319919]
  We introduce Cross-Care, the first benchmark framework dedicated to assessing biases and real world knowledge in large language models (LLMs) We evaluate how demographic biases embedded in pre-training corpora like $ThePile$ influence the outputs of LLMs. Our results highlight substantial misalignment between LLM representation of disease prevalence and real disease prevalence rates across demographic subgroups.
  arXiv  Detail & Related papers  (2024-05-09T02:33:14Z)
• Inspecting Model Fairness in Ultrasound Segmentation Tasks [20.281029492841878]
  We inspect a series of deep learning (DL) segmentation models using two ultrasound datasets. Our findings reveal that even state-of-the-art DL algorithms demonstrate unfair behavior in ultrasound segmentation tasks. These results serve as a crucial warning, underscoring the necessity for careful model evaluation before their deployment in real-world scenarios.
  arXiv  Detail & Related papers  (2023-12-05T05:08:08Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• 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)
• Targeted Data Augmentation for bias mitigation [0.0]
  We introduce a novel and efficient approach for addressing biases called Targeted Data Augmentation (TDA) Unlike the laborious task of removing biases, our method proposes to insert biases instead, resulting in improved performance. To identify biases, we annotated two diverse datasets: a dataset of clinical skin lesions and a dataset of male and female faces.
  arXiv  Detail & Related papers  (2023-08-22T12:25:49Z)
• Analyzing Bias in Diffusion-based Face Generation Models [75.80072686374564]
  Diffusion models are increasingly popular in synthetic data generation and image editing applications. We investigate the presence of bias in diffusion-based face generation models with respect to attributes such as gender, race, and age. We examine how dataset size affects the attribute composition and perceptual quality of both diffusion and Generative Adversarial Network (GAN) based face generation models.
  arXiv  Detail & Related papers  (2023-05-10T18:22:31Z)
• Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis [3.5536769591744557]
  Deep learning (DL) models have shown great success in many medical image analysis tasks. However, deployment of the resulting models into real clinical contexts requires robustness and fairness across different sub-populations. Recent studies have shown significant biases in DL models across demographic subgroups, indicating a lack of fairness in the models.
  arXiv  Detail & Related papers  (2023-03-06T16:01:30Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)
• LOGAN: Local Group Bias Detection by Clustering [86.38331353310114]
  We argue that evaluating bias at the corpus level is not enough for understanding how biases are embedded in a model. We propose LOGAN, a new bias detection technique based on clustering. Experiments on toxicity classification and object classification tasks show that LOGAN identifies bias in a local region.
  arXiv  Detail & Related papers  (2020-10-06T16:42:51Z)

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.