Xudong Liu

Xudong Liu

Auto-generated profile, based on publicly available information

Xudong Liu

Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
1 January 2019
Verified
Conference Paper
Open access
PDF file
KSKai Sun
Kai Sun
RZRichong Zhang
Richong Zhang
SMSamuel Mensah
Samuel Mensah
YMYongyi Mao
Yongyi Mao
XLXudong Liu
Xudong Liu
Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, Xudong Liu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.


8 April 2023 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
KSKai Sun
Kai Sun
RZRichong Zhang
Richong Zhang
SMSamuel Mensah
Samuel Mensah
YMYongyi Mao
Yongyi Mao
XLXudong Liu
Xudong Liu
Information extraction aims at extracting entities, relations, and so on, in text to support information retrieval systems. To extract information, researchers have considered multitask learning (ML) approaches. The conventional ML approach learns shared features across tasks, with the assumption that these features capture sufficient task interactions to learn expressive shared representations for task classification. However, such an assumption is flawed in different perspectives. First, the shared representation may contain noise introduced by another task; tasks coupled for multitask learning may have different complexities but this approach treats all tasks equally; the conventional approach has a flat structure that hinders the learning of explicit interactions. This approach, however, learns implicit interactions across tasks and often has a generalization ability that has benefited the learning of multitasks. In this article, we take advantage of implicit interactions learned by conventional approaches while alleviating the issues mentioned above by developing a Recurrent Interaction Network with an effective Early Prediction Integration (RIN-EPI) for multitask learning. Specifically, RIN-EPI learns implicit and explicit interactions across two different but related tasks. To effectively learn explicit interactions across tasks, we consider the correlations among the outputs of related tasks. It is, however, obvious that task outputs are unobservable during training, so we leverage the predictions at intermediate layers (referred to as early predictions) as proxies as well as shared features across tasks to learn explicit interactions through attention mechanisms and sequence learning models. By recurrently learning explicit interactions, we gradually improve predictions for the individual tasks in the multitask learning. We demonstrate the effectiveness of RIN-EPI on the learning of two mainstream multitasks for information extraction: (1) entity recognition and relation classification and (2) aspect and opinion term co-extraction. Extensive experiments demonstrate the effectiveness of the RIN-EPI architecture, where we achieve state-of-the-art results on several benchmark datasets.

27 June 2024 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
XWXu Wang
Xu Wang
HYHongwei Yu
Hongwei Yu
XMXiangxin Meng
Xiangxin Meng
HCHongliang Cao
Hongliang Cao
Hongyu ZhangHongyu Zhang
Hongyu Zhang
CHChunming Hu
Chunming Hu
Fault localization (FL) and automated program repair (APR) are two main tasks of automatic software debugging. Compared with traditional methods, deep learning-based approaches have been demonstrated to achieve better performance in FL and APR tasks. However, the existing deep learning-based FL methods ignore the deep semantic features or only consider simple code representations. And for APR tasks, existing template-based APR methods are weak in selecting the correct fix templates for more effective program repair, which are also not able to synthesize patches via the embedded end-to-end code modification knowledge obtained by training models on large-scale bug-fix code pairs. Moreover, in most of FL and APR methods, the model designs and training phases are performed separately, leading to ineffective sharing of updated parameters and extracted knowledge during the training process. This limitation hinders the further improvement in the performance of FL and APR tasks. To solve the above problems, we propose a novel approach called MTL-TRANSFER, which leverages a multi-task learning strategy to extract deep semantic features and transferred knowledge from different perspectives. First, we construct a large-scale open-source bug datasets and implement 11 multi-task learning models for bug detection and patch generation sub-tasks on 11 commonly used bug types, as well as one multi-classifier to learn the relevant semantics for the subsequent fix template selection task. Second, an MLP-based ranking model is leveraged to fuse spectrum-based, mutation-based and semantic-based features to generate a sorted list of suspicious statements. Third, we combine the patches generated by the neural patch generation sub-task from the multi-task learning strategy with the optimized fix template selecting order gained from the multi-classifier mentioned above. Finally, the more accurate FL results, the optimized fix template selecting order, and the expanded patch candidates are combined together to further enhance the overall performance of APR tasks. Our extensive experiments on widely-used benchmark Defects4J show that MTL-TRANSFER outperforms all baselines in FL and APR tasks, proving the effectiveness of our approach. Compared with our previously proposed FL method TRANSFER-FL (which is also the state-of-the-art statement-level FL method), MTL-TRANSFER increases the faults hit by 8/11/12 on Top-1/3/5 metrics (92/159/183 in total). And on APR tasks, the number of successfully repaired bugs of MTL-TRANSFER under the perfect localization setting reaches 75, which is 8 more than our previous APR method TRANSFER-PR. Furthermore, another experiment to simulate the actual repair scenarios shows that MTL-TRANSFER can successfully repair 15 and 9 more bugs (56 in total) compared with TBar and TRANSFER, which demonstrates the effectiveness of the combination of our optimized FL and APR components.

26 July 2023 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
CLChen Liu
Chen Liu
BLBo Li
Bo Li
JZJun Zhao
Jun Zhao
XLXudong Liu
Xudong Liu
CLChunpei Li
Chunpei Li
Foretelling ongoing malware attacks in real time is challenging due to the stealthy and polymorphic nature of their executive behavior patterns. In this paper, we present MalAF, a novel Mal ware A ttack F oretelling framework that utilizes run-time behavior (i.e., sequences of API events) of malware to foretell the attack that has not yet executed. MalAF first samples suspicious API events by assessing the sensitivity of the parameters of each API event and dividing them into multiple attack time slots by calculating the strong correlation. Following that, MalAF employs dynamic heterogeneous graph sequences to incrementally model contextual semantics for each attack time slot, generating malware state sequences in real time. Moreover, MalAF proposes a greedy adaptive dictionary (GAD)-optimized IRL preference learning method to automate the capture of families' intrinsic attack preferences, which achieves higher performance than the existing inverse reinforcement learning (IRL). Additionally, with the guidance of families' attack preferences, MalAF trains an LSTM to foretell the future path of the target malware. Finally, MalAF matches the identified APIs' paths with a malicious capability base and reports the comprehensible attacks to an analyst. The experiments on real-world datasets demonstrate that our proposed MalAF outperforms the state-of-the-art methods, which improves the baseline by 3.01% $\sim$ 4.73% of accuracy in terms of path foretell.

6 January 2021 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
SZShihui Zheng
Shihui Zheng
XLXudong Liu
Xudong Liu
SZShoujin Zang
Shoujin Zang
YDYihao Deng
Yihao Deng
DHDongqi Huang
Dongqi Huang
COChanghai Ou
Changhai Ou
A transient fault-based collision attack always requires to inject fault multiple times. We present the first attack that uses collision information caused by a persistent fault in the substitution box (S-box) to recover the entire 128-bit key of the advanced encryption standard (AES). Moreover, a relatively relaxed fault model is required; i.e., the attacker does not know any information about the position, the length (i.e., the number of bytes), or the value of the injected fault. At most, 4096 chosen plaintexts are required for a persistent fault-based collision attack (PFCA), and the computational complexity is O(2 23 ) in the worst case in the single-byte fault setting. A filtering algorithm is presented in the multibyte fault setting, and we theoretically prove that the complexity can be reduced to O(2 12 ) in more than half of cases if the number of collision ciphertexts follows a uniform distribution. In addition, PFCAs against a software implementation of AES are simulated on a laptop, and the results show that the success probability of the attack either with online key searching or with offline key searching approaches 100%. In particular, more than 97% of all experiments output the right key with complexity O(2 12 ) in the multibyte fault setting. Therefore, the attack is more efficient in this scenario. Furthermore, the attack works on an AES implementation protected by Boolean masking. Finally, PFCAs against AES implementations separately protected by two widely used countermeasures-the inverse S-box and the parity-1 matrix-are performed. The experimental results illustrate that only a 10-round protection using the first method can completely defeat the attack.