Deep learning models for medical image analysis demonstrate remarkable diagnostic accuracy but remain highly vulnerable to adversarial perturbations. To address this challenge, we introduce Foveated Adversarial Purification (FAP), a biologically inspired preprocessing pipeline that integrates three core innovations. First, FAP employs eccentricity-adaptive separable Gaussian blurring, where kernel size dynamically adjusts with lesion morphology. This approach mimics the human fovea's acuity gradient, preserves high-frequency details around lesions while suppressing peripheral noise, and reduces GPU memory usage by 40% compared to conventional 2D filtering. Second, FAP introduces gradient-guided fixation sampling with sigmoid-clustered probability, which prioritizes lesion-dense regions consistent with radiologists' diagnostic scanpaths. This mechanism achieves 82% overlap with radiologist-annotated regions of interest, ensuring that preprocessing aligns with clinical saliency rather than arbitrary regions. Third, FAP implements lesion-aware adversarial training, where binary spatial masks confine perturbations to non-diagnostic regions. This preserves lesion fidelity while hardening the classifier against attacks, yielding a certified ℓ2radius of 1.12, exceeding prior defenses. Evaluated across three mammography datasets, FAP achieves substantial robustness improvements: +20.03% absolute accuracy on CMMD (coarse tumors), +16.39% on BREAST (mixed lesions), and maintains baseline performance on CBIS-DDSM (microcalcifications). By aligning computational robustness with biological vision strategies, FAP establishes a clinically interpretable and computationally efficient framework for adversarial defense in medical imaging. The implementation is released in our GitHub repository11https://github.com/ghazallalooha/FAP.

Prompt learning has garnered attention for its efficiency over traditional model training and fine-tuning. However, existing methods, constrained by inadequate theoretical foundations, encounter difficulties in achieving causally invariant prompts, ultimately falling short of capturing robust features that generalize effectively across categories. To address these challenges, we introduce the DiCap model, a theoretically grounded Diffusion-based Counterfactual prompt learning framework, which leverages a diffusion process to iteratively sample gradients from the marginal and conditional distributions of the causal model, guiding the generation of counterfactuals that satisfy the minimal sufficiency criterion. Grounded in rigorous theoretical derivations, this approach guarantees the identifiability of counterfactual outcomes while imposing strict bounds on estimation errors. We further employ a contrastive learning framework that leverages the generated counterfactuals, thereby enabling the refined extraction of prompts that are precisely aligned with the causal features of the data. Extensive experimental results demonstrate that our method performs excellently across tasks such as image classification, image-text retrieval, and visual question answering, with particularly strong advantages in unseen categories.

Instrumental variables (IVs), widely applied in economics and healthcare, enable consistent counterfactual prediction in the presence of hidden confounding factors, effectively addressing endogeneity issues. The prevailing IV-based counterfactual prediction methods typically rely on the availability of valid IVs (satisfying Relevance, Exclusivity, and Exogeneity), a requirement which often proves elusive in real-world scenarios. Various data-driven techniques are being developed to create valid IVs (or representations of IVs) from a pool of IV candidates. However, most of these techniques still necessitate the inclusion of valid IVs within the set of candidates. This paper proposes a distribution-conditioned adversarial variational autoencoder to tackle this challenge. Specifically: 1) for Relevance and Exclusivity, we deduce the corresponding evidence lower bound following the Bayesian network structure and build the variational autoencoder; accordingly, 2) for Exogeneity , we design an adversarial game to encourage latent factors originating from the marginal distribution, compelling the independence between IVs and other outcome-related factors. Extensive experimental results validate the effectiveness, stability and generality of our proposed model in generating valid IV factors in the absence of valid IV candidates.

The advancements in disentangled representation learning significantly enhance the accuracy of counterfactual predictions by granting precise control over instrumental variables, confounders, and adjustable variables. An appealing method for achieving the independent separation of these factors is mutual information minimization, a task that presents challenges in numerous machine learning scenarios, especially within high-dimensional spaces. To circumvent this challenge, we propose the Self-Distilled Disentanglement framework, referred to as SD2. Grounded in information theory, it ensures theoretically sound independent disentangled representations without intricate mutual information estimator designs for high-dimensional representations. Our comprehensive experiments, conducted on both synthetic and real-world datasets, confirms the effectiveness of our approach in facilitating counterfactual inference in the presence of both observed and unobserved confounders.

Inferring causal effects on observational data has been widely adopted in various fields. One of the cornerstones of causal inference research, named Individual Treatment Effects (ITE) estimation, aims to predict the expected difference between the treatment and control outcome. It provides a more precise solution to meeting personalized needs while enhancing prediction accuracy in machine learning tasks. Nevertheless, the lack of counterfactual truth and selection bias remain the main challenges in ITE estimation and exert detrimental effects on inference accuracy. In this work, we propose a novel Contrastive Individual Treatment Effects (CITE) estimation framework to alleviate both above issues. Based on the contrastive task designed for causal inference, we fully exploit the self-supervision information hidden in data to achieve balanced and predictive representations while appropriately leveraging causal prior knowledge. Our method outperforms the state-of-the-art ITE estimation algorithms on several real-world and semi-synthetic datasets, which validates its efficacy and superiority.