Search Results for author: Yuanyuan Yuan

Found 13 papers, 8 papers with code

Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learning

no code implementations3 Feb 2024 Ao Sun, Yuanyuan Yuan, Pingchuan Ma, Shuai Wang

This paper alleviates the information leakage issue by introducing label supervision in concept predication and constructing a hierarchical concept set.

No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML

1 code implementation11 Oct 2023 Ziqi Zhang, Chen Gong, Yifeng Cai, Yuanyuan Yuan, Bingyan Liu, Ding Li, Yao Guo, Xiangqun Chen

These solutions, referred to as TEE-Shielded DNN Partition (TSDP), partition a DNN model into two parts, offloading the privacy-insensitive part to the GPU while shielding the privacy-sensitive part within the TEE.

Inference Attack Membership Inference Attack

Unveiling Single-Bit-Flip Attacks on DNN Executables

no code implementations12 Sep 2023 Yanzuo Chen, Zhibo Liu, Yuanyuan Yuan, Sihang Hu, Tianxiang Li, Shuai Wang

Nevertheless, we find that DNN executables contain extensive, severe (e. g., single-bit flip), and transferrable attack surfaces that are not present in high-level DNN models and can be exploited to deplete full model intelligence and control output labels.

Precise and Generalized Robustness Certification for Neural Networks

1 code implementation11 Jun 2023 Yuanyuan Yuan, Shuai Wang, Zhendong Su

We identify two key properties, independence and continuity, that convert the latent space into a precise and analysis-friendly input space representation for certification.

Autonomous Driving Style Transfer

Explain Any Concept: Segment Anything Meets Concept-Based Explanation

1 code implementation NeurIPS 2023 Ao Sun, Pingchuan Ma, Yuanyuan Yuan, Shuai Wang

For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying important pixels, and emerging concept-based XAI explore forming explanations with concepts (e. g., a head in an image).

Instance Segmentation Semantic Segmentation

Decompiling x86 Deep Neural Network Executables

no code implementations3 Oct 2022 Zhibo Liu, Yuanyuan Yuan, Shuai Wang, Xiaofei Xie, Lei Ma

BTD takes DNN executables and outputs full model specifications, including types of DNN operators, network topology, dimensions, and parameters that are (nearly) identical to those of the input models.

ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems

1 code implementation8 Jan 2022 Qi Pang, Yuanyuan Yuan, Shuai Wang, Wenting Zheng

Vertical federated learning (VFL) system has recently become prominent as a concept to process data distributed across many individual sources without the need to centralize it.

Federated Learning Privacy Preserving

Automated Side Channel Analysis of Media Software with Manifold Learning

1 code implementation9 Dec 2021 Yuanyuan Yuan, Qi Pang, Shuai Wang

Recent advances in representation learning and perceptual learning inspired us to consider the reconstruction of media inputs from side channel traces as a cross-modality manifold learning task that can be addressed in a unified manner with an autoencoder framework trained to learn the mapping between media inputs and side channel observations.

Cloud Computing Representation Learning +1

MDPFuzz: Testing Models Solving Markov Decision Processes

no code implementations6 Dec 2021 Qi Pang, Yuanyuan Yuan, Shuai Wang

During fuzzing, MDPFuzz decides which mutated state to retain by measuring if it can reduce cumulative rewards or form a new state sequence.

Autonomous Driving Collision Avoidance +2

Provably Valid and Diverse Mutations of Real-World Media Data for DNN Testing

no code implementations3 Dec 2021 Yuanyuan Yuan, Qi Pang, Shuai Wang

In contrast, we discuss the feasibility of mutating real-world media data with provably high DIV and VAL based on manifold.

DNN Testing valid

Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion

1 code implementation3 Dec 2021 Yuanyuan Yuan, Qi Pang, Shuai Wang

We demonstrate that NLC is significantly correlated with the diversity of a test suite across a number of tasks (classification and generation) and data formats (image and text).

DNN Testing Test

Perception Matters: Detecting Perception Failures of VQA Models Using Metamorphic Testing

1 code implementation CVPR 2021 Yuanyuan Yuan, Shuai Wang, Mingyue Jiang, Tsong Yueh Chen

MetaVQA checks whether the answer to (i, q) satisfies metamorphic relationships (MRs), denoting perception consistency, with the composed answers of transformed questions and images.

Benchmarking DNN Testing +2

Private Image Reconstruction from System Side Channels Using Generative Models

2 code implementations ICLR 2021 Yuanyuan Yuan, Shuai Wang, Junping Zhang

Given the ever-growing adoption of machine learning as a service (MLaaS), image analysis software on cloud platforms has been exploited by reconstructing private user images from system side channels.

Image Reconstruction Side Channel Analysis

Cannot find the paper you are looking for? You can Submit a new open access paper.