Unveiling Security, Privacy, and Ethical Concerns of ChatGPT

This paper delves into the realm of ChatGPT, an AI-powered chatbot that utilizes topic modeling and reinforcement learning to generate natural responses. Although ChatGPT holds immense promise across various industries, such as customer service, education, mental health treatment, personal productivity, and content creation, it is essential to address its security, privacy, and ethical implications. By exploring the upgrade path from GPT-1 to GPT-4, discussing the model's features, limitations, and potential applications, this study aims to shed light on the potential risks of integrating ChatGPT into our daily lives. Focusing on security, privacy, and ethics issues, we highlight the challenges these concerns pose for widespread adoption. Finally, we analyze the open problems in these areas, calling for concerted efforts to ensure the development of secure and ethically sound large language models.

Provable Multi-instance Deep AUC Maximization with Stochastic Pooling

This paper considers a novel application of deep AUC maximization (DAM) for multi-instance learning (MIL), in which a single class label is assigned to a bag of instances (e.g., multiple 2D slices of a CT scan for a patient). We address a neglected yet non-negligible computational challenge of MIL in the context of DAM, i.e., bag size is too large to be loaded into {GPU} memory for backpropagation, which is required by the standard pooling methods of MIL. To tackle this challenge, we propose variance-reduced stochastic pooling methods in the spirit of stochastic optimization by formulating the loss function over the pooled prediction as a multi-level compositional function. By synthesizing techniques from stochastic compositional optimization and non-convex min-max optimization, we propose a unified and provable muli-instance DAM (MIDAM) algorithm with stochastic smoothed-max pooling or stochastic attention-based pooling, which only samples a few instances for each bag to compute a stochastic gradient estimator and to update the model parameter. We establish a similar convergence rate of the proposed MIDAM algorithm as the state-of-the-art DAM algorithms. Our extensive experiments on conventional MIL datasets and medical datasets demonstrate the superiority of our MIDAM algorithm.

Interaction design for socially assistive robots for people with developmental disabilities

Social robots, also known as service or assistant robots, have been developed to improve the quality of human life in recent years. Socially assistive robots (SAR) are a special type of social robots that focus on providing support through social interaction. The design of socially capable and intelligent robots can vary, depending on the target user groups. In this work, I assess the effect of socially assistive robots' roles, functions, and communication approaches in the context of a social agent providing service or companionship to users with developmental disabilities. In this thesis, I describe an exploratory study of interaction design for a socially assistive robot that supports people suffering from developmental disabilities. While exploring the impacts of visual elements to robot's visual interface and different aspects of robot's social dimension, I developed a series of prototypes and tested them through three user studies that included three residents with various function levels at a local group home for people with developmental disabilities. All user studies had been recorded for the following qualitative data analysis. Results show that each design factor played a different role in delivering information and in increasing engagement, and there are more aspects of HRI to consider besides robot's graphical user interface and speech, such as proxemics and robot's physical appearance and dimensions. I also note that some fundamental design principles that would work for ordinary users did not apply to our target user group. I conclude that socially assistive robots could benefit our target users and acknowledge that these robots were not suitable for certain scenarios based on the feedback from our users.

A deep learning network with differentiable dynamic programming for retina OCT surface segmentation

Multiple-surface segmentation in Optical Coherence Tomography (OCT) images is a challenge problem, further complicated by the frequent presence of weak image boundaries. Recently, many deep learning (DL) based methods have been developed for this task and yield remarkable performance. Unfortunately, due to the scarcity of training data in medical imaging, it is challenging for DL networks to learn the global structure of the target surfaces, including surface smoothness. To bridge this gap, this study proposes to seamlessly unify a U-Net for feature learning with a constrained differentiable dynamic programming module to achieve an end-to-end learning for retina OCT surface segmentation to explicitly enforce surface smoothness. It effectively utilizes the feedback from the downstream model optimization module to guide feature learning, yielding a better enforcement of global structures of the target surfaces. Experiments on Duke AMD (age-related macular degeneration) and JHU MS (multiple sclerosis) OCT datasets for retinal layer segmentation demonstrated very promising segmentation accuracy.

Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choices

The area under the ROC curve (AUROC) has been vigorously applied for imbalanced classification and moreover combined with deep learning techniques. However, there is no existing work that provides sound information for peers to choose appropriate deep AUROC maximization techniques. In this work, we fill this gap from three aspects. (i) We benchmark a variety of loss functions with different algorithmic choices for deep AUROC optimization problem. We study the loss functions in two categories: pairwise loss and composite loss, which includes a total of 10 loss functions. Interestingly, we find composite loss, as an innovative loss function class, shows more competitive performance than pairwise loss from both training convergence and testing generalization perspectives. Nevertheless, data with more corrupted labels favors a pairwise symmetric loss. (ii) Moreover, we benchmark and highlight the essential algorithmic choices such as positive sampling rate, regularization, normalization/activation, and optimizers. Key findings include: higher positive sampling rate is likely to be beneficial for deep AUROC maximization; different datasets favors different weights of regularizations; appropriate normalization techniques, such as sigmoid and $\ell_2$ score normalization, could improve model performance. (iii) For optimization aspect, we benchmark SGD-type, Momentum-type, and Adam-type optimizers for both pairwise and composite loss. Our findings show that although Adam-type method is more competitive from training perspective, but it does not outperform others from testing perspective.

When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee

In this paper, we propose systematic and efficient gradient-based methods for both one-way and two-way partial AUC (pAUC) maximization that are applicable to deep learning. We propose new formulations of pAUC surrogate objectives by using the distributionally robust optimization (DRO) to define the loss for each individual positive data. We consider two formulations of DRO, one of which is based on conditional-value-at-risk (CVaR) that yields a non-smooth but exact estimator for pAUC, and another one is based on a KL divergence regularized DRO that yields an inexact but smooth (soft) estimator for pAUC. For both one-way and two-way pAUC maximization, we propose two algorithms and prove their convergence for optimizing their two formulations, respectively. Experiments demonstrate the effectiveness of the proposed algorithms for pAUC maximization for deep learning on various datasets.

Joint Calibrationless Reconstruction and Segmentation of Parallel MRI

The volume estimation of brain regions from MRI data is a key problem in many clinical applications, where the acquisition of data at high spatial resolution is desirable. While parallel MRI and constrained image reconstruction algorithms can accelerate the scans, image reconstruction artifacts are inevitable, especially at high acceleration factors. We introduce a novel image domain deep-learning framework for calibrationless parallel MRI reconstruction, coupled with a segmentation network to improve image quality and to reduce the vulnerability of current segmentation algorithms to image artifacts resulting from acceleration. The combination of the proposed image domain deep calibrationless approach with the segmentation algorithm offers improved image quality, while increasing the accuracy of the segmentations. The novel architecture with an encoder shared between the reconstruction and segmentation tasks is seen to reduce the need for segmented training datasets. In particular, the proposed few-shot training strategy requires only 10% of segmented datasets to offer good performance.

Identifying Similar Movie Characters Quickly but Effectively Using Non-exhaustive Pair-wise Attention

Identifying similar movie characters is a captivating task that can be our first step to understand the commonalities between human characteristics and experiences. Here, we seek to identify similar movie character descriptions and evaluate our findings based on whether they belong to a common fan-curated trope (theme). Rather than simply comparing the embedding representation of character description, we use a pair-wise attention model to make use of complex word/span-level relationships across the two character descriptions to predict the similarity of the two characters. Naively, such a model would require the exhaustive comparison of each character to all other characters, which is an O(n^2) operation with respect to the number of characters, making it unfeasible to be used in practice. We reduced this into an O(n) operation using a two-step approach that involves choosing only a tiny fraction of character-pairs to perform pairwise attention on while still being effective in this task. Our approach performs at least 9-27% better than methods based on state-of-the-art paragraph embedding representations.

Globally Optimal Segmentation of Mutually Interacting Surfaces using Deep Learning

Segmentation of multiple surfaces in medical images is a challenging problem, further complicated by the frequent presence of weak boundary and mutual influence between adjacent objects. The traditional graph-based optimal surface segmentation method has proven its effectiveness with its ability of capturing various surface priors in a uniform graph model. However, its efficacy heavily relies on handcrafted features that are used to define the surface cost for the "goodness" of a surface. Recently, deep learning (DL) is emerging as powerful tools for medical image segmentation thanks to its superior feature learning capability. Unfortunately, due to the scarcity of training data in medical imaging, it is nontrivial for DL networks to implicitly learn the global structure of the target surfaces, including surface interactions. In this work, we propose to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters. The multiple optimal surfaces are then simultaneously detected by minimizing the total surface cost while explicitly enforcing the mutual surface interaction constraints. The optimization problem is solved by the primal-dual Internal Point Method, which can be implemented by a layer of neural networks, enabling efficient end-to-end training of the whole network. Experiments on Spectral Domain Optical Coherence Tomography (SD-OCT) retinal layer segmentation and Intravascular Ultrasound (IVUS) vessel wall segmentation demonstrated very promising results. All source code is public to facilitate further research at this direction.