arXiv subjects

Jason Lin

Publications and source records attributed to Jason Lin.

10 recordsLinked to original sources

arXiv2025

Privy: Envisioning and Mitigating Privacy Risks for Consumer-facing AI Product Concepts

AI creates and exacerbates privacy risks, yet practitioners lack effective resources to identify and mitigate these risks. We present Privy, a tool that guides practitioners without privacy expertise through structured privacy impact assessments to: (i) identify relevant risks in novel AI product concepts, and (ii) propose appropriate mitigations. Privy was shaped by a formative study with 11 practitioners, which informed two versions -- one LLM-powered, the other template-based. We evaluated these two versions of Privy through a between-subjects, controlled study with 24 separate practitioners, whose assessments were reviewed by 13 independent privacy experts. Results show that Privy helps practitioners produce privacy assessments that experts deemed high quality: practitioners identified relevant risks and proposed appropriate mitigation strategies. These effects were augmented in the LLM-powered version. Practitioners themselves rated Privy as being useful and usable, and their feedback illustrates how it helps overcome long-standing awareness, motivation, and ability barriers in privacy work.

cs.HC↗

arXiv2025

The NIAID Discovery Portal: A Unified Search Engine for Infectious and Immune-Mediated Disease Datasets

The NIAID Data Ecosystem Discovery Portal (https://data.niaid.nih.gov) provides a unified search interface for over 4 million datasets relevant to infectious and immune-mediated disease (IID) research. Integrating metadata from domain-specific and generalist repositories, the Portal enables researchers to identify and access datasets using user-friendly filters or advanced queries, without requiring technical expertise. The Portal supports discovery of a wide range of resources, including epidemiological, clinical, and multi-omic datasets, and is designed to accommodate exploratory browsing and precise searches. The Portal provides filters, prebuilt queries, and dataset collections to simplify the discovery process for users. The Portal additionally provides documentation and an API for programmatic access to harmonized metadata. By easing access barriers to important biomedical datasets, the NIAID Data Ecosystem Discovery Portal serves as an entry point for researchers working to understand, diagnose, or treat IID. Valuable datasets are often overlooked because they are difficult to locate. The NIAID Data Ecosystem Discovery Portal fills this gap by providing a centralized, searchable interface that empowers users with varying levels of technical expertise to find and reuse data. By standardizing key metadata fields and harmonizing heterogeneous formats, the Portal improves data findability, accessibility, and reusability. This resource supports hypothesis generation, comparative analysis, and secondary use of public data by the IID research community, including those funded by NIAID. The Portal supports data sharing by standardizing metadata and linking to source repositories, and maximizes the impact of public investment in research data by supporting scientific advancement via secondary use.

cs.DB↗

arXiv2024

WebQuest: A Benchmark for Multimodal QA on Web Page Sequences

The rise of powerful multimodal LLMs has enhanced the viability of building web agents which can, with increasing levels of autonomy, assist users to retrieve information and complete tasks on various human-computer interfaces. It is hence necessary to build challenging benchmarks that span a wide-variety of use cases reflecting real-world usage. In this work, we present WebQuest, a multi-page question-answering dataset that requires reasoning across multiple related web pages. In contrast to existing UI benchmarks that focus on multi-step web navigation and task completion, our dataset evaluates information extraction, multimodal retrieval and composition of information from many web pages. WebQuest includes three question categories: single-screen QA, multi-screen QA, and QA based on navigation traces. We evaluate leading proprietary multimodal models like GPT-4V, Gemini Flash, Claude 3, and open source models like InstructBLIP, PaliGemma on our dataset, revealing a significant gap between single-screen and multi-screen reasoning. Finally, we investigate inference time techniques like Chain-of-Thought prompting to improve model capabilities on multi-screen reasoning.

cs.IR↗

arXiv2024

ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe screens to Large Language Models and automatically generate question-answering (QA), UI navigation, and summarization training datasets at scale. We run ablation studies to demonstrate the impact of these design choices. At only 5B parameters, ScreenAI achieves new state-of-the-artresults on UI- and infographics-based tasks (Multi-page DocVQA, WebSRC, MoTIF and Widget Captioning), and new best-in-class performance on others (Chart QA, DocVQA, and InfographicVQA) compared to models of similar size. Finally, we release three new datasets: one focused on the screen annotation task and two others focused on question answering.

cs.CV↗

arXiv2023

Explore, Establish, Exploit: Red Teaming Language Models from Scratch

Deploying large language models (LMs) can pose hazards from harmful outputs such as toxic or false text. Prior work has introduced automated tools that elicit harmful outputs to identify these risks. While this is a valuable step toward securing models, these approaches rely on a pre-existing way to efficiently classify undesirable outputs. Using a pre-existing classifier does not allow for red-teaming to be tailored to the target model. Furthermore, when failures can be easily classified in advance, red-teaming has limited marginal value because problems can be avoided by simply filtering training data and/or model outputs. Here, we consider red-teaming "from scratch," in which the adversary does not begin with a way to classify failures. Our framework consists of three steps: 1) Exploring the model's range of behaviors in the desired context; 2) Establishing a definition and measurement for undesired behavior (e.g., a classifier trained to reflect human evaluations); and 3) Exploiting the model's flaws using this measure to develop diverse adversarial prompts. We use this approach to red-team GPT-3 to discover classes of inputs that elicit false statements. In doing so, we construct the CommonClaim dataset of 20,000 statements labeled by humans as common-knowledge-true, common knowledge-false, or neither. We are making code and data available.

cs.CL↗

arXiv2023

Zorro: the masked multimodal transformer

Attention-based models are appealing for multimodal processing because inputs from multiple modalities can be concatenated and fed to a single backbone network - thus requiring very little fusion engineering. The resulting representations are however fully entangled throughout the network, which may not always be desirable: in learning, contrastive audio-visual self-supervised learning requires independent audio and visual features to operate, otherwise learning collapses; in inference, evaluation of audio-visual models should be possible on benchmarks having just audio or just video. In this paper, we introduce Zorro, a technique that uses masks to control how inputs from each modality are routed inside Transformers, keeping some parts of the representation modality-pure. We apply this technique to three popular transformer-based architectures (ViT, Swin and HiP) and show that with contrastive pre-training Zorro achieves state-of-the-art results on most relevant benchmarks for multimodal tasks (AudioSet and VGGSound). Furthermore, the resulting models are able to perform unimodal inference on both video and audio benchmarks such as Kinetics-400 or ESC-50.

cs.CV↗

arXiv2022

ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots

We introduce ScreenQA, a novel benchmarking dataset designed to advance screen content understanding through question answering. The existing screen datasets are focused either on low-level structural and component understanding, or on a much higher-level composite task such as navigation and task completion for autonomous agents. ScreenQA attempts to bridge this gap. By annotating 86k question-answer pairs over the RICO dataset, we aim to benchmark the screen reading comprehension capacity, thereby laying the foundation for vision-based automation over screenshots. Our annotations encompass full answers, short answer phrases, and corresponding UI contents with bounding boxes, enabling four subtasks to address various application scenarios. We evaluate the dataset's efficacy using both open-weight and proprietary models in zero-shot, fine-tuned, and transfer learning settings. We further demonstrate positive transfer to web applications, highlighting its potential beyond mobile applications.

cs.CL↗

arXiv2021

Multiparty Mediated Quantum Secret Sharing Protocol

This study proposes a multiparty mediated quantum secret sharing (MQSS) protocol that allows n restricted quantum users to share a secret via the assistance of a dishonest third-party (TP) with full quantum capabilities. Under the premise that a restricted quantum user can only perform the Hadamard transformation and the Z-basis measurement, the proposed MQSS protocol has addressed two common challenges in the existing semi-quantum secret sharing protocols: (1) the dealer must have full quantum capability, and (2) the classical users must equip with the wavelength quantum filter and the photon number splitters (PNS) to detect the Trojan horse attacks. The security analysis has also delivered proof to show that the proposed MQSS protocol can avoid the collective attack, the collusion attack, and the Trojan horse attacks. In addition, the proposed MQSS protocol is more efficient than the existing SQSS protocols due to the restricted quantum users can only equip with two quantum operations, and the qubits are transmitted within a shorter distance.

cs.CR↗

arXiv2018

Interactive Classification for Deep Learning Interpretation

We present an interactive system enabling users to manipulate images to explore the robustness and sensitivity of deep learning image classifiers. Using modern web technologies to run in-browser inference, users can remove image features using inpainting algorithms and obtain new classifications in real time, which allows them to ask a variety of "what if" questions by experimentally modifying images and seeing how the model reacts. Our system allows users to compare and contrast what image regions humans and machine learning models use for classification, revealing a wide range of surprising results ranging from spectacular failures (e.g., a "water bottle" image becomes a "concert" when removing a person) to impressive resilience (e.g., a "baseball player" image remains correctly classified even without a glove or base). We demonstrate our system at The 2018 Conference on Computer Vision and Pattern Recognition (CVPR) for the audience to try it live. Our system is open-sourced at https://github.com/poloclub/interactive-classification. A video demo is available at https://youtu.be/llub5GcOF6w.

cs.CV↗

arXiv2011

Comment on "Semiquantum secret sharing using entangled states"

Recently, Li et al. [Phys. Rev. A, 82(2), 022303] presented two semi-quantum secret sharing (SQSS) protocols using GHZ-like states. The proposed schemes are rather practical because only the secret dealer requires to equip with advanced quantum devices such as quantum memory, whereas the other agents can merely perform classical operations to complete the secret sharing. However, this study points out that a security pitfall exists in the eavesdropping check phase of both schemes that could mount to an Intercept-resend attack and a Trojan horse attack on the two schemes, respectively, to disclose the other agent's shadow, and further to reveal the master key of the SQSS, which contradicts to the security requirement of a QSS. Fortunately, two possible solutions are proposed to avoid this security pitfall.

quant-ph↗