Hyunjun Lee

Hyunjun Lee, Junhyun Lee, Taehwa Choi et al.

Time-to-event analysis, also known as survival analysis, aims to predict the time of occurrence of an event, given a set of features. One of the major challenges in this area is dealing with censored data, which can make learning algorithms more complex. Traditional methods such as Cox's proportional hazards model and the accelerated failure time (AFT) model have been popular in this field, but they often require assumptions such as proportional hazards and linearity. In particular, the AFT models often require pre-specified parametric distributional assumptions. To improve predictive performance and alleviate strict assumptions, there have been many deep learning approaches for hazard-based models in recent years. However, representation learning for AFT has not been widely explored in the neural network literature, despite its simplicity and interpretability in comparison to hazard-focused methods. In this work, we introduce the Deep AFT Rank-regression model for Time-to-event prediction (DART). This model uses an objective function based on Gehan's rank statistic, which is efficient and reliable for representation learning. On top of eliminating the requirement to establish a baseline event time distribution, DART retains the advantages of directly predicting event time in standard AFT models. The proposed method is a semiparametric approach to AFT modeling that does not impose any distributional assumptions on the survival time distribution. This also eliminates the need for additional hyperparameters or complex model architectures, unlike existing neural network-based AFT models. Through quantitative analysis on various benchmark datasets, we have shown that DART has significant potential for modeling high-throughput censored time-to-event data.

Junhyeong Cho, Youngseok Yoon, Hyeonjun Lee et al.

Grounded Situation Recognition (GSR) is the task that not only classifies a salient action (verb), but also predicts entities (nouns) associated with semantic roles and their locations in the given image. Inspired by the remarkable success of Transformers in vision tasks, we propose a GSR model based on a Transformer encoder-decoder architecture. The attention mechanism of our model enables accurate verb classification by capturing high-level semantic feature of an image effectively, and allows the model to flexibly deal with the complicated and image-dependent relations between entities for improved noun classification and localization. Our model is the first Transformer architecture for GSR, and achieves the state of the art in every evaluation metric on the SWiG benchmark. Our code is available at https://github.com/jhcho99/gsrtr .

Behnaz Hassanshahi, Hyunjun Lee, Paddy Krishnan et al.

Even though a lot of effort has been invested in analyzing client-side web applications during the past decade, the existing tools often fail to deal with the complexity of modern JavaScript applications. However, from an attacker point of view, the client side of such web applications can reveal invaluable information about the server side. In this paper, first we study the existing tools and enumerate the most crucial features a security-aware client-side analysis should be supporting. Next, we propose GELATO to detect vulnerabilities in modern client-side JavaScript applications that are built upon complex libraries and frameworks. In particular, we take the first step in closing the gap between state-aware crawling and client-side security analysis by proposing a feedback-driven security-aware guided crawler that is able to analyze complex frameworks automatically, and increase the coverage of security-sensitive parts of the program efficiently. Moreover, we propose a new lightweight client-side taint analysis that outperforms the start-of-the-art tools, requires no modification to browsers, and reports non-trivial taint flows on modern JavaScript applications.