Yanjun Wu

Yanjun Wu

Auto-generated profile, based on publicly available information

Yanjun Wu

Institute of Software, Chinese Academy of Sciences

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 April 2024
Verified
Conference Paper
Open access
YCYuxiao Chen
Yuxiao Chen
JWJingzheng Wu
Jingzheng Wu
XLXiang Ling
Xiang Ling
CLChangjiang Li
Changjiang Li
ZRZhiqing Rui
Zhiqing Rui
YWYanjun Wu
Yanjun Wu

11 November 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
LZLibo Zhang
Libo Zhang
DDDawei Du
Dawei Du
CLCongcong Li
Congcong Li
YWYanjun Wu
Yanjun Wu
LTLuo Tiejian
Luo Tiejian
Automatic Check-Out (ACO) provides an object detection based mechanism for retailers to process the purchases of customers automatically. However, it suffers a lot from the domain shift problem because of different data distribution between the single item in training exemplar images and mixed items in testing checkout images. In this paper, we propose a new iterative knowledge distillation method to solve the domain adaptation problem for this task. First, we develop a new augmentation data strategy to generate synthesized checkout images. It can extract segmented items from the training images by the coarse-to-fine strategy and filter items with unrealistic poses by pose pruning. Second, we propose a dual pyramid scale network (DPSNet) to exploit the multi-scale feature representation in joint detection and counting views. Third, the iterative knowledge distillation training strategy is developed to make full use of both image-level and instance-level samples to narrow the semantic gap between source domain and target domain. Extensive experiments on the large-scale Retail Product Checkout (RPC) dataset show the proposed DPSNet can achieve state-of-the-art performance compared with existing methods. The source codes can be found at https://isrc.iscas.ac.cn/gitlab/research/dpsnet.

14 November 2023
Verified
Book Chapter
Closed access
PDF file
JZJinzhi Zheng
Jinzhi Zheng
RJRuyi Ji
Ruyi Ji
LZLibo Zhang
Libo Zhang
YWYanjun Wu
Yanjun Wu
CZChen Zhao
Chen Zhao

28 December 2024 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
KYKaichun Yao
Kaichun Yao
HWHao Wang
Hao Wang
CQChuan Qin
Chuan Qin
HZHengshu Zhu
Hengshu Zhu
YWYanjun Wu
Yanjun Wu
LZLibo Zhang
Libo Zhang
Code based adversarial attacks play a crucial role in revealing vulnerabilities of software system. Recently, pre-trained programming language models (PLMs) have demonstrated remarkable success in various significant software engineering tasks, progressively transforming the paradigm of software development. Despite their impressive capabilities, these powerful models are vulnerable to adversarial attacks. Therefore, it is necessary to carefully investigate the robustness and vulnerabilities of the PLMs by means of adversarial attacks. Adversarial attacks entail imperceptible input modifications that cause target models to make incorrect predictions. Existing approaches for attacking PLMs often employ either identifier renaming or the greedy algorithm, which may yield sub-optimal performance or lead to high inference times. In response to these limitations, we propose CARL, an unsupervised black-box attack model that leverages reinforcement learning to generate imperceptible adversarial examples. Specifically, CARL comprises a programming language encoder and a perturbation prediction layer. In order to achieve more effective and efficient attack, we cast the task as a sequence decision-making process, optimizing through policy gradient with a suite of reward functions. We conduct extensive experiments to validate the effectiveness of CARL on code summarization, code translation, and code refinement tasks, covering various programming languages and PLMs. The experimental results demonstrate that CARL surpasses state-of-the-art code attack models, achieving the highest attack success rate across multiple tasks and PLMs while maintaining high attack efficiency, imperceptibility, consistency, and fluency.

1 November 2012
Verified
Conference Paper
Closed access
BDBaozeng Ding
Baozeng Ding
YHYeping He
Yeping He
YWYanjun Wu
Yanjun Wu
AMAlex Miller
Alex Miller
JCJohn Criswell
John Criswell
Baggy Bounds Checking is a backward-compatible defense against out-of-bounds errors. It is reported as being faster than any previous bounds checking tool. However, it enforces allocation bounds instead of object bounds and thus cannot detect memory errors that are in padding areas. In this paper, we present BBAC: a technique that extends Baggy Bounds Checking to enforce accurate bounds checking. The key insight behind our approach is to store the object size at the end of the padding area, making it efficient to lookup object bounds meta-data at runtime. We show experimentally that BBAC can detect more memory errors than Baggy Bounds Checking. Our experiments also show that BBAC only adds an additional 4.39% performance overhead over the original Baggy Bounds Checking technique for the Olden benchmarks and 2x overhead at most on the real-world applications we tested.

1 February 2019 in Neurocomputing
Verified
Journal Article
Closed access
FWFuzhang Wu
Fuzhang Wu
YKYan Kong
Yan Kong
WDWeiming Dong
Weiming Dong
YWYanjun Wu
Yanjun Wu