Yiran Chen

DeepObfuscator: Adversarial Training Framework for Privacy-Preserving Image Classification

2019 · arXiv (Cornell University)

Deep learning has been widely utilized in many computer vision applications and achieved remarkable commercial success. However, running deep learning models on mobile devices is generally challenging due to limitation of the available computing resources. …

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability

2020 · arXiv (Cornell University)

We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers. Rather than focusing on crossing decision boundaries at the output layer of the source model, …

Fine-grained Out-of-Distribution Detection with Mixup Outlier Exposure.

2021 · arXiv (Cornell University)

Enabling out-of-distribution (OOD) detection for DNNs is critical for their safe and reliable operation in the open world. Unfortunately, current works in both methodology and evaluation focus on rather contrived detection problems, and only consider …

Rethink before Releasing Your Model

2023

Machine learning (ML)-based techniques for electronic design automation (EDA) have boosted the performance of modern integrated circuits (ICs). Such achievement makes ML model to be of importance for the EDA industry. In addition, ML models …

Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments

2023 · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Many real-world scenarios in which DNN-based recognition systems are deployed have inherently fine-grained attributes (e.g., bird-species recognition, medical image classification). In addition to achieving reliable accuracy, a critical subtask for these models is to detect …

Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap

2025 · arXiv (Cornell University)

We present Voice Evaluation of Reasoning Ability (VERA), a benchmark for evaluating reasoning ability in voice-interactive systems under real-time conversational constraints. VERA comprises 2,931 voice-native episodes derived from established text benchmarks and organized into five …

Extractive Summarization as Text Matching

2020

This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. Instead of following the commonly used framework of extracting sentences individually and modeling the relationship between sentences, we …