diff --git a/_publications/2024-01-13-Breast.md b/_publications/2024-01-13-Breast.md
new file mode 100644
index 0000000..b301c6d
--- /dev/null
+++ b/_publications/2024-01-13-Breast.md
@@ -0,0 +1,28 @@
+---
+title: "Validation report 004: Breast Cancer Detector Model"
+collection: publications
+permalink: /publication/2024-01-13-Breast
+excerpt: "This study conducts a Red Teaming analysis on a CNN-based Breast Cancer Detector Model, using XAI techniques to assess its reliability and uncover vulnerabilities. The analysis found that while the model is generally robust, certain intricate vulnerabilities could be exposed through data augmentation and out-of-distribution samples. LIME and SHAP analyses highlighted important phenomena, emphasizing the need for high-quality input data to ensure model reliability in clinical applications."
+date: 2024-01-13
+venue: 'Explainable Machine Learning 2023/2024 course'
+paperurl: 'https://modeloriented.github.io/CVE-AI/files/2023_Breast.pdf'
+citation: 'Mikolaj Drzewiecki, Monika Michaluk. (2024). &quot;Red Teaming analysis of the Breast Cancer Detector Model.&quot; <i>Github: ModelOriented/CVE-AI</i>.'
+tags:
+  - BreCaHAD
+  - Breast Histopathology Images
+  - LIME
+  - SHAP
+---
+
+This study conducts a Red Teaming analysis on the Breast Cancer Detector Model, a Convolutional Neural Network designed for predicting breast cancer from tissue scans. Using eXplainable Artificial Intelligence (XAI) techniques, we assess the model’s reliability, investigating influences from unintended artifacts and evaluating its generalization with out-of-distribution samples. Our aim is to uncover vulnerabilities and enhance the model’s robustness in clinical applications.
+
+<hr/>
+
+Performed analysis proved strength of the model. Various vulnerabilities we were able to find turned out to be very intricate, unlike to be revealed in day to day usage. We assess the uncertainty while classifying the sample as infected tissue, to be promising field to improve.
+
+We can conclude that phenomena discovered during LIME and SHAP analysis are deeply connected to this problem. Also, we advise care in ensuring the quality of input data, as vulnerabilities involving data augmentation were exposed.
+
+<hr/>
+
+Link to original datasets: [Breast Histopathology Images](https://www.kaggle.com/datasets/paultimothymooney/breast-histopathology-images), [BreCaHAD](https://www.kaggle.com/datasets/truthisneverlinear/brecahad).
+
diff --git a/files/2023_Breast.pdf b/files/2023_Breast.pdf
new file mode 100644
index 0000000..0a96edc
Binary files /dev/null and b/files/2023_Breast.pdf differ