Galex: Exploring the Evolution and Intersection of Disciplines

AdversaFlow: Visual Red Teaming for Large Language Models with Multi-Level Adversarial Flow

Large Language Models (LLMs) are powerful but also raise significant security concerns, particularly regarding the harm they can cause, such as generating fake news that manipulates public opinion on social media and providing responses to unethical activities. Traditional red teaming approaches for identifying AI vulnerabilities rely on manual prompt construction and expertise. This paper introduces AdversaFlow, a novel visual analytics system designed to enhance LLM security against adversarial attacks through human-AI collaboration. AdversaFlow involves adversarial training between a target model and a red model, featuring unique multi-level adversarial flow and fluctuation path visualizations. These features provide insights into adversarial dynamics and LLM robustness, enabling experts to identify and mitigate vulnerabilities effectively. We present quantitative evaluations and case studies validating our system's utility and offering insights for future AI security solutions. Our method can enhance LLM security, supporting downstream scenarios like social media regulation by enabling more effective detection, monitoring, and mitigation of harmful content and behaviors.

Dual Space Coupling Model Guided Overlap-Free Scatterplot

The overdraw problem of scatterplots seriously interferes with the visual tasks. Existing methods, such as data sampling, node dispersion, subspace mapping, and visual abstraction, cannot guarantee the correspondence and consistency between the data points that reflect the intrinsic original data distribution and the corresponding visual units that reveal the presented data distribution, thus failing to obtain an overlap-free scatterplot with unbiased and lossless data distribution. A dual space coupling model is proposed in this paper to represent the complex bilateral relationship between data space and visual space theoretically and analytically. Under the guidance of the model, an overlap-free scatterplot method is developed through integration of the following: a geometry-based data transformation algorithm, namely DistributionTranscriptor; an efficient spatial mutual exclusion guided view transformation algorithm, namely PolarPacking; an overlap-free oriented visual encoding configuration model and a radius adjustment tool, namely f_rdraw. Our method can ensure complete and accurate information transfer between the two spaces, maintaining consistency between the newly created scatterplot and the original data distribution on global and local features. Quantitative evaluation proves our remarkable progress on computational efficiency compared with the state-of-the-art methods. Three applications involving pattern enhancement, interaction improvement, and overdraw mitigation of trajectory visualization demonstrate the broad prospects of our method.

A Framework for Multiclass Contour Visualization

Multiclass contour visualization is often used to interpret complex data attributes in such fields as weather forecasting, computational fluid dynamics, and artificial intelligence. However, effective and accurate representations of underlying data patterns and correlations can be challenging in multiclass contour visualization, primarily due to the inevitable visual cluttering and occlusions when the number of classes is significant. To address this issue, visualization design must carefully choose design parameters to make visualization more comprehensible. With this goal in mind, we proposed a framework for multiclass contour visualization. The framework has two components: a set of four visualization design parameters, which are developed based on an extensive review of literature on contour visualization, and a declarative domain-specific language (DSL) for creating multiclass contour rendering, which enables a fast exploration of those design parameters. A task-oriented user study was conducted to assess how those design parameters affect users' interpretations of real-world data. The study results offered some suggestions on the value choices of design parameters in multiclass contour visualization.