Existing defenses attempt to bolster the resilience of GNNs using diverse approaches.

Modern foundational models increasingly reflect not just world knowledge, but patterns of human preference embedded in their training data. We hypothesize that recursive alignment-via human feedback and model-generated corpora-induces a social desirability bias, nudging models to favor agreeable or flattering responses over objective reasoning. We refer to it as the Narcissus Hypothesis and test it across 31 models using standardized personality assessments and a novel Social Desirability Bias score. Results reveal a significant drift toward socially conforming traits, with profound implications for corpus integrity and the reliability of downstream inferences. We then offer a novel epistemological interpretation, tracing how recursive bias may collapse higher-order reasoning down Pearl's Ladder of Causality, culminating in what we refer to as the Rung of Illusion.

The adversarial robustness of Graph Neural Networks (GNNs) has been questioned due to the false sense of security uncovered by strong adaptive attacks despite the existence of numerous defenses. In this work, we delve into the robustness analysis of representative robust GNNs and provide a unified robust estimation point of view to understand their robustness and limitations. Our novel analysis of estimation bias motivates the design of a robust and unbiased graph signal estimator. We then develop an efficient Quasi-Newton iterative reweighted least squares algorithm to solve the estimation problem, which unfolds as robust unbiased aggregation layers in GNNs with a theoretical convergence guarantee. Our comprehensive experiments confirm the strong robustness of our proposed model, and the ablation study provides a deep understanding of its advantages.