Robust medical image classification under input corruption and bag-level annotation remains a critical challenge in clinical AI applications. We propose QAPNet, a Quantum- Attentive Patchwise Network that integrates quantum neural encoding, additive attention-based instance reweighting, and prototype-contrastive regularization for reliable diagnosis from degraded inputs. Our framework uses a sliding-window strategy to divide each MRI medical Image into overlapping patches, where each is encoded via an 8-qubit quantum circuit using RY -based noise-sensitive layers for yielding expressive low-dimensional representations without relying on classical CNNs. A lightweight additive attention mechanism computes instance-wise importance weights that enable interpretable and noise-aware bag-level aggregation. To enhance robustness, we apply a contrastive loss that aligns clean and noisy embeddings and enforce prototype-guided clustering via class-wise centroids. We evaluate QAPNet across seven benchmark medical imaging datasets under three levels of additive Gaussian noise (σ ∈ {5%, 10%, 30%}). QAPNet consistently outperforms eight strong baselines and achieves up to +20.8% higher accuracy in OASIS (with 30% noise), +17.7% in PathMNIST, and maintains stable performance (< 4% degradation) in all settings. Ablation studies confirm the critical role of quantum encoding, attention-based aggregation, and prototype contrastive learning. These results suggest that QAPNet offers a scalable and interpretable architecture for noisy medical imaging tasks in the real world to bridge the quantum representation learning with robust clinical prediction.

Graph neural networks (GNNs) excel at modeling graph-structured data but often inherit and amplify biases, leading to substantial efforts in developing fair GNNs. However, most existing approaches assume full access to sensitive attribute information, which is often impractical in real-world scenarios due to privacy concerns or risks of discrimination. To address this limitation, this paper focuses on graph fairness with limited sensitive attribute information, ensuring applicability to real-world contexts where current methods fall short. Specifically, we introduce an innovative fairness optimization strategy, propose a novel framework named FGLISA, and provide a theoretical perspective linking limited sensitive attribute information access to fairness objectives, thus enabling fair graph learning in real-world applications with limited sensitive attribute information. Experiments on diverse real-world datasets and tasks validate the effectiveness of our approach in achieving both fairness and predictive performance.

Large Language Models (LLMs) are increasingly deployed in finance, where unsafe behavior can lead to serious compliance and regulatory risks.However, most red-teaming research focuses on overtly harmful content and overlooks attacks that appear legitimate on the surface yet induce compliance-violating responses.We address this gap by introducing a controllable black-box multi-turn riskconcealed red-teaming framework (CoRT) that progressively conceals surface-level risk while exploiting non-compliant behaviors.CoRT contains two key components: (i) a Risk Concealment Attacker (RCA) that generates multi-turn prompts via iterative refinement, and (ii) a Risk Concealment Controller (RCC) that predicts a turn-level Risk Concealment Score (RCS) to steer RCA's follow-up style.We also build a domain-specific benchmark, FIN-Bench, with 522 instructions spanning six financial risk categories.Experiments on nine widely used LLMs show that CoRT (RCA) achieves 93.19% average attack success rate (ASR), and CoRT (RCA+RCC) further improves the average ASR to 95.00%.

The way research and business manage and utilize knowledge is undergoing a significant transformation, driven by Artificial Intelligence (AI). Deep learning and machine learning are emerging as powerful tools for optimizing knowledge management systems, leading to more informed and productive development. AI offers unique solutions for organizations struggling with information overload and inefficient knowledge transfer. These AI models can significantly improve data management and utilization. Imagine an AI-powered system that streamlines onboarding processes, provides precise answers to various queries, and even captures the valuable tacit knowledge (implicit skills and expertise) often residing within individuals. AI bridges the gap between explicit knowledge (easily documented information) and tacit knowledge, fostering a more comprehensive and accessible knowledge base. However, such AI systems solicit trustworthy and responsible approaches to mitigate potential misuse and malfunction. In this workshop, we aim to gather researchers and engineers from academia and industry to discuss the latest advances in trustworthy and responsible AI solutions for information and knowledge management systems.

In recent years, plentiful evidence illustrates that Graph Convolutional Networks (GCNs) achieve extraordinary accomplishments on the node classification task. However, GCNs may be vulnerable to adversarial attacks on label-scarce dynamic graphs. Many existing works aim to strengthen the robustness of GCNs; for instance, adversarial training is used to shield GCNs against malicious perturbations. However, these works fail on dynamic graphs for which label scarcity is a pressing issue. To overcome label scarcity, self-training attempts to iteratively assign pseudo-labels to highly confident unlabeled nodes but such attempts may suffer serious degradation under dynamic graph perturbations. In this paper, we generalize noisy supervision as a kind of self-supervised learning method and then propose a novel Bayesian self-supervision model, namely GraphSS, to address the issue. Extensive experiments demonstrate that GraphSS can not only affirmatively alert the perturbations on dynamic graphs but also effectively recover the prediction of a node classifier when the graph is under such perturbations. These two advantages prove to be generalized over three classic GCNs across five public graph datasets.

Node classification using Graph Neural Networks (GNNs) has been widely applied in various real-world scenarios. However, in recent years, compelling evidence emerges that the performance of GNN-based node classification may deteriorate substantially by topological perturbation, such as random connections or adversarial attacks. Various solutions, such as topological denoising methods and mechanism design methods, have been proposed to develop robust GNN-based node classifiers but none of these works can fully address the problems related to topological perturbations. Recently, the Bayesian label transition model is proposed to tackle this issue but its slow convergence may lead to inferior performance. In this work, we propose a new label inference model, namely LInDT, which integrates both Bayesian label transition and topology-based label propagation for improving the robustness of GNNs against topological perturbations. LInDT is superior to existing label transition methods as it improves the label prediction of uncertain nodes by utilizing neighborhood-based label propagation leading to better convergence of label inference. Besides, LIndT adopts asymmetric Dirichlet distribution as a prior, which also helps it to improve label inference. Extensive experiments on five graph datasets demonstrate the superiority of LInDT for GNN-based node classification under three scenarios of topological perturbations.

Online social networks (OSNs) classify users into different categories based on their online activities and interests, a task which is referred as a node classification task. Such a task can be solved effectively using Graph Convolutional Networks (GCNs). However, a small number of users, so-called perturbators, may perform random activities on an OSN, which significantly deteriorate the performance of a GCN-based node classification task. Existing works in this direction defend GCNs either by adversarial training or by identifying the attacker nodes followed by their removal. However, both of these approaches require that the attack patterns or attacker nodes be identified first, which is difficult in the scenario when the number of perturbator nodes is very small. In this work, we develop a GCN defense model, namely GraphLT1, which uses the concept of label transition. GraphLT assumes that perturbators' random activities deteriorate GCN's performance. To overcome this issue, GraphLT subsequently uses a novel Bayesian label transition model, which takes GCN's predicted labels and applies label transitions by Gibbs-sampling-based inference and thus repairs GCN's prediction to achieve better node classification. Extensive experiments on seven benchmark datasets show that GraphLT considerably enhances the performance of the node classifier in an unperturbed environment; furthermore, it validates that GraphLT can successfully repair a GCN-based node classifier with superior performance than several competing methods.

Since the emergence of the Silk Road market in the early 2010s, dark web `cryptomarkets' have proliferated and offered people an online platform to buy and sell illicit drugs, relying on cryptocurrencies such as Bitcoin for anonymous transactions. However, recent studies have highlighted the potential for de-anonymization of bitcoin transactions, bringing into question the level of anonymity afforded by cryptomarkets. We examine a set of over 100,000 product reviews from several cryptomarkets collected in 2018 and 2019 and conduct a comprehensive analysis of the markets, including an examination of the distribution of drug sales and revenue among vendors, and a comparison of incidences of opioid sales to overdose deaths in a US city. We explore the potential for de-anonymization of vendors by implementing a Naïve-Bayes classifier to predict the vendor from a given product review, and attempt to link vendors' sales to specific Bitcoin transactions. On the buyer side, we evaluate the efficacy of hierarchical agglomerative clustering for grouping together transactions corresponding to the same buyer. We find that the high degree of specialization among the small subset of high-revenue vendors may render these vendors susceptible to de-anonymization. Further research is necessary to confirm these findings, which are restricted by the scarcity of ground-truth data for validation.

White matter hyperintensities (WMH) is one of main consequences of small vessel diseases. Automated WMH segmentation techniques play an important role in clinical research and practice. U-Net has been demonstrated to yield the best precise segmentation results so far. However, sometimes it losses more detailed information as network goes deeper. In addition, it usually depends on data augmentation or a large number of filters. Large filters increase the complexity of model, which may be an obstacle for real-time segmentation on cloud computing. To solve these two issues, a new architecture, Lighter U-Net is proposed to reinforce feature use, to reduce the number of parameters as well as to retain sufficient receptive fields without losing resolution. The extensive experiments suggest that the proposed network achieves comparable performance as the state-of-the-art methods by only using 17% parameters of standard U-Net.