Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the safety protocols of LLMs. To address this issue, LLMs are regularly updated with safety patches based on reported jailbreak prompts. However, malicious users often keep their successful jailbreak prompts private to exploit LLMs. To uncover these private jailbreak prompts, extensive analysis of large-scale conversational datasets is necessary to identify prompts that still manage to bypass the system's defenses. This task is highly challenging due to the immense volume of conversation data, diverse characteristics of jailbreak prompts, and their presence in complex multi-turn conversations. To tackle these challenges, we introduce JailbreakHunter, a visual analytics approach for identifying jailbreak prompts in large-scale human-LLM conversational datasets. We have designed a workflow with three analysis levels: group-level, conversation-level, and turn-level. Group-level analysis enables users to grasp the distribution of conversations and identify suspicious conversations using multiple criteria, such as similarity with reported jailbreak prompts in previous research and attack success rates. Conversation-level analysis facilitates the understanding of the progress of conversations and helps discover jailbreak prompts within their conversation contexts. Turn-level analysis allows users to explore the semantic similarity and token overlap between a single-turn prompt and the reported jailbreak prompts, aiding in the identification of new jailbreak strategies. The effectiveness and usability of the system were verified through multiple case studies and expert interviews.

Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts-unwanted biases in the benchmark datasets-can damage the effectiveness of benchmark datasets in revealing models' real capabilities. Since shortcuts vary in coverage, productivity, and semantic meaning, it is challenging for NLU experts to systematically understand and avoid them when creating benchmark datasets. In this paper, we develop a visual analytics system, ShortcutLens, to help NLU experts explore shortcuts in NLU benchmark datasets. The system allows users to conduct multi-level exploration of shortcuts. Specifically, Statistics View helps users grasp the statistics such as coverage and productivity of shortcuts in the benchmark dataset. Template View employs hierarchical and interpretable templates to summarize different types of shortcuts. Instance View allows users to check the corresponding instances covered by the shortcuts. We conduct case studies and expert interviews to evaluate the effectiveness and usability of the system. The results demonstrate that ShortcutLens supports users in gaining a better understanding of benchmark dataset issues through shortcuts, inspiring them to create challenging and pertinent benchmark datasets.

Recently, large pretrained language models have achieved compelling performance on commonsense benchmarks. Nevertheless, it is unclear what commonsense knowledge the models learn and whether they solely exploit spurious patterns. Feature attributions are popular explainability techniques that identify important input concepts for model outputs. However, commonsense knowledge tends to be implicit and rarely explicitly presented in inputs. These methods cannot infer models' implicit reasoning over mentioned concepts. We present CommonsenseVIS, a visual explanatory system that utilizes external commonsense knowledge bases to contextualize model behavior for commonsense question-answering. Specifically, we extract relevant commonsense knowledge in inputs as references to align model behavior with human knowledge. Our system features multi-level visualization and interactive model probing and editing for different concepts and their underlying relations. Through a user study, we show that CommonsenseVIS helps NLP experts conduct a systematic and scalable visual analysis of models' relational reasoning over concepts in different situations.

Machine learning prediction APIs offered by Google, Microsoft, Amazon, and many other providers have been continuously adopted in a plethora of applications, such as visual object detection, natural language comprehension, and speech recognition. Despite the importance of a systematic study and comparison of different APIs over time, this topic is currently under-explored because of the lack of data and user-friendly exploration tools. To address this issue, we present HAPI Explorer (History of API Explorer), an interactive system that offers easy access to millions of instances of commercial API applications collected in three years, prioritize attention on user-defined instance regimes, and explain interesting patterns across different APIs, subpopulations, and time periods via visual and natural languages. HAPI Explorer can facilitate further comprehension and exploitation of ML prediction APIs.

Graph Neural Networks (GNNs) aim to extend deep learning techniques to graph data and have achieved significant progress in graph analysis tasks (e.g., node classification) in recent years. However, similar to other deep neural networks like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), GNNs behave like a black box with their details hidden from model developers and users. It is therefore difficult to diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs and RNNs, little research has addressed the challenges for GNNs. This paper fills the research gap with an interactive visual analysis tool, GNNLens, to assist model developers and users in understanding and analyzing GNNs. Specifically, Parallel Sets View and Projection View enable users to quickly identify and validate error patterns in the set of wrong predictions; Graph View and Feature Matrix View offer a detailed analysis of individual nodes to assist users in forming hypotheses about the error patterns. Since GNNs jointly model the graph structure and the node features, we reveal the relative influences of the two types of information by comparing the predictions of three models: GNN, Multi-Layer Perceptron (MLP), and GNN Without Using Features (GNNWUF). Two case studies and interviews with domain experts demonstrate the effectiveness of GNNLens in facilitating the understanding of GNN models and their errors.

Commercial ML APIs offered by providers such as Google, Amazon and Microsoft have dramatically simplified ML adoptions in many applications. Numerous companies and academics pay to use ML APIs for tasks such as object detection, OCR and sentiment analysis. Different ML APIs tackling the same task can have very heterogeneous performances. Moreover, the ML models underlying the APIs also evolve over time. As ML APIs rapidly become a valuable marketplace and an integral part of analytics, it is critical to systematically study and compare different APIs with each other and to characterize how individual APIs change over time. However, this practically important topic is currently underexplored due to the lack of data. In this paper, we present HAPI (History of APIs), a longitudinal dataset of 1,761,417 instances of commercial ML API applications (involving APIs from Amazon, Google, IBM, Microsoft and other providers) across diverse tasks including image tagging, speech recognition, and text mining from 2020 to 2022. Each instance consists of a query input for an API (e.g., an image or text) along with the API’s output prediction/annotation and confidence scores. HAPI is the first large-scale dataset of ML API usages and is a unique resource for studying ML as-a-service (MLaaS). As examples of the types of analyses that HAPI enables, we show that ML APIs’ performance changes substantially over time—several APIs’ accuracies dropped on specific benchmark datasets. Even when the API’s aggregate performance stays steady, its error modes can shift across different subtypes of data between 2020 and 2022. Such changes can substantially impact the entire analytics pipelines that use some ML API as a component. We further use HAPI to study commercial APIs’ performance disparities across demographic subgroups over time. HAPI can stimulate more research in the growing field of MLaaS.

Multimodal sentiment analysis aims to recognize people's attitudes from multiple communication channels such as verbal content (i.e., text), voice, and facial expressions. It has become a vibrant and important research topic in natural language processing. Much research focuses on modeling the complex intra- and inter-modal interactions between different communication channels. However, current multimodal models with strong performance are often deep-learning-based techniques and work like black boxes. It is not clear how models utilize multimodal information for sentiment predictions. Despite recent advances in techniques for enhancing the explainability of machine learning models, they often target unimodal scenarios (e.g., images, sentences), and little research has been done on explaining multimodal models. In this paper, we present an interactive visual analytics system, M2Lens, to visualize and explain multimodal models for sentiment analysis. M2Lens provides explanations on intra- and inter-modal interactions at the global, subset, and local levels. Specifically, it summarizes the influence of three typical interaction types (i.e., dominance, complement, and conflict) on the model predictions. Moreover, M2Lens identifies frequent and influential multimodal features and supports the multi-faceted exploration of model behaviors from language, acoustic, and visual modalities. Through two case studies and expert interviews, we demonstrate our system can help users gain deep insights into the multimodal models for sentiment analysis.

Node-link diagrams are widely used to facilitate network explorations. However, when using a graph drawing technique to visualize networks, users often need to tune different algorithm-specific parameters iteratively by comparing the corresponding drawing results in order to achieve a desired visual effect. This trial and error process is often tedious and time-consuming, especially for non-expert users. Inspired by the powerful data modelling and prediction capabilities of deep learning techniques, we explore the possibility of applying deep learning techniques to graph drawing. Specifically, we propose using a graph-LSTM-based approach to directly map network structures to graph drawings. Given a set of layout examples as the training dataset, we train the proposed graph-LSTM-based model to capture their layout characteristics. Then, the trained model is used to generate graph drawings in a similar style for new networks. We evaluated the proposed approach on two special types of layouts (i.e., grid layouts and star layouts) and two general types of layouts (i.e., ForceAtlas2 and PivotMDS) in both qualitative and quantitative ways. The results provide support for the effectiveness of our approach. We also conducted a time cost assessment on the drawings of small graphs with 20 to 50 nodes. We further report the lessons we learned and discuss the limitations and future work.

To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space, it is impossible to try all models. Users tend to distrust automatic results and increase the search budget as much as they can, thereby undermining the efficiency of AutoML. To address these issues, we design and implement ATMSeer, an interactive visualization tool that supports users in refining the search space of AutoML and in analyzing the results. To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts. A multi-granularity visualization is proposed to enable users to monitor the AutoML process, analyze the searched models, and refine the search space in real time. We demonstrate the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users.

Wireless Sensor Networks (WSNs) often contain a large number of nodes. In order to organize nodes efficiently for a long lifespan, clustering algorithm is demanded in WSNs to reduce redundant data transmissions and to save energy. We propose a novel clustering algorithm to create reliable and energy-aware clusters for in-network data processing. The clustering algorithm is a new service on a publish/subscribe middleware called Mires. The goal is to improve load balancing and robustness. Our clustering algorithm considers location information to facilitate boundary control. We conducted simulations to evaluate performance and energy efficiency. We implemented a prototype for feasibility demonstration.

The idea of multisensor integration is to use multiple sensors for measuring the same variables, where each sensor has its own accuracy, reliability and drawbacks. The sensor information is integrated by some data integration algorithms. In this paper, Radial Basis Function (RBF) neural networks and multisensor data fusion technology are combined and used in the fault detection and diagnosis of sensors hardware faults in the Satellite Attitude Measurement System (SAMS). The fusion method of the RBF neural networks is adopted. By using the combination method the outputs of the system are more accurate and reliable than each individual sensor. Research results show that this method for the detection and diagnosis of the sensors hardware faults in the SAMS is feasible and more effective, and for the sensors which measure the same attitude angle, using the method of firstly integration, then faults diagnosis, finally connection with the measurement system, the systematic measurement precision and performance-price-ratio can be improved.

When designing Kalman filter for INS/GPS, usually position and velocity are chosen as the measuring variables. With the development of GPS attitude determination, GPS has already been able to measure the carrier's attitudes. So attitude can be augmented as the measuring variables. In this paper a new INS/GPS integrated navigation System is designed, in which position, velocity and attitude are chosen as the measuring variables. The observation equation of this new marine INS/GPS integrated navigation system is deduced in detail. Simulation results show that the evaluation precision and velocity of the navigation parameters are effectively improved in the new integrated navigation system.

The attitude control of a future satellite is facing the challenge of its uncertain model because of flexural bodies coupling to the center body. This paper proposes a neuro-fuzzy approach to control the uncertain dynamics and disturbance. The flexible model of solar array is extended to the satellite attitude equation. To overcome the variation of internal parameters and external disturbances, three adaptive neuro-fuzzy controllers are applied to realize the attitude and orbit control system (AOCS) on the base of Proportional-Integral-Differential (PID) controllers. A least square estimation method is combined with gradient descent learning in order to optimize the learning error universally during train procedure. Simulation results show the neuro-fuzzy controllers have good performance to abate influence from disturbance, fadeless vibration and the change of the satellite's inertia parameters.