Da Xiao

Da Xiao

Auto-generated profile, based on publicly available information

Da Xiao

Beijing University of Posts and Telecommunications

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
6 March 2023 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
HLHongliang Liang
Hongliang Liang
XLXiangyu Li
Xiangyu Li
DXDa Xiao
Da Xiao
JLJie Liu
Jie Liu
YZYanjie Zhou
Yanjie Zhou
JLJin Li
Jin Li
Web Application Firewalls (WAFs) are widely deployed to protect key web applications against multiple security threats, so it is important to test WAFs regularly to prevent attackers from bypassing them easily. Machine-learning-based black-box WAF testing is gaining more attention, though existing learning-based approaches have strict requirements on the source and scale of payload data and suffer from the local optimum problem, limiting their effectiveness and practical application. We propose GPTFuzzer, a practical and effective generation-based approach to test WAFs by generating attack payloads token-by-token. Specifically, we fine-tune a Generative Pre-trained Transformer language model with reinforcement learning to make GPTFuzzer have the least restrictions on payload data and thus more applicable in practice, and we use reward modeling and KL-divergence penalty to improve the effectiveness of our approach and mitigate the local optimum issue. We implement GPTFuzzer and evaluate it on two well-known open-source WAFs against three kinds of common attacks. Experimental results show that GPTFuzzer significantly outperforms state-of-the-art approaches, i.e. ML-Driven and RAT, finding up to 7.8× (3.2× on average) more bypassing payloads within 1,250,000 requests, or finding out all bypassing payloads using up to 8.1× (3.3× on average) fewer requests.

4 March 2015 in arXiv
Verified
Preprint
Open access
PDF file
IGIan J. Goodfellow
Ian J. Goodfellow
MMMehdi Mirza
Mehdi Mirza
DXDa Xiao
Da Xiao
ACAaron Courville
Aaron Courville
YBYoshua BENGIO
Yoshua BENGIO
Catastrophic forgetting is a problem faced by many machine learning models and algorithms. When trained on one task, then trained on a second task, many machine learning models "forget" how to perform the first task. This is widely believed to be a serious problem for neural networks. Here, we investigate the extent to which the catastrophic forgetting problem occurs for modern neural networks, comparing both established and recent gradient-based training algorithms and activation functions. We also examine the effect of the relationship between the first task and the second task on catastrophic forgetting. We find that it is always best to train using the dropout algorithm--the dropout algorithm is consistently best at adapting to the new task, remembering the old task, and has the best tradeoff curve between these two extremes. We find that different tasks and relationships between tasks result in very different rankings of activation function performance. This suggests the choice of activation function should always be cross-validated.

8 January 2022 in Empirical Software Engineering
Verified
Journal Article
Closed access
PDF file
DXDa Xiao
Da Xiao
DHDengji Hang
Dengji Hang
LALu Ai
Lu Ai
SLShengping Li
Shengping Li
HLHongliang Liang
Hongliang Liang

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
RNRuikang Ni
Ruikang Ni
DXDa Xiao
Da Xiao
QMQingye Meng
Qingye Meng
XLXiangyu Li
Xiangyu Li
SZShihui Zheng
Shihui Zheng
HLHongliang Liang
Hongliang Liang
Compositional relational reasoning (CRR) is a hallmark of human intelligence, but we lack a clear understanding of whether and how existing transformer large language models (LLMs) can solve CRR tasks. To enable systematic exploration of the CRR capability of LLMs, we first propose a new synthetic benchmark called Generalized Associative Recall (GAR) by integrating and generalizing the essence of several tasks in mechanistic interpretability (MI) study in a unified framework. Evaluation shows that GAR is challenging enough for existing LLMs, revealing their fundamental deficiency in CRR. Meanwhile, it is easy enough for systematic MI study. Then, to understand how LLMs solve GAR tasks, we use attribution patching to discover the core circuits reused by Vicuna-33B across different tasks, and a set of vital attention heads. Intervention experiments show that the correct functioning of these heads significantly impacts task performance. Especially, we identify two classes of heads whose activations represent the abstract notion of true and false in GAR tasks respectively. They play fundamental roles in CRR across various models and tasks.

6 February 2019
Verified
Book Chapter
Open access
PDF file
DXDa Xiao
Da Xiao
SBShouying Bai
Shouying Bai
QWQian Wu
Qian Wu
BCBaojiang Cui
Baojiang Cui
This paper proposes an obfuscation algorithm based on congruence equation and knapsack problem, for the problem of generating opaque predicate in control flow obfuscation. We binarize the state of the solution of the congruence equation, and then combine the knapsack problem to achieve the binary output of opaque predicate. Compared with the existing chaotic opaque predicate design algorithm, the experimental comparison shows that this paper generates the probability of opaque predicate binary results is nearly 50%, and the time overhead is controlled within 1 s. The experimental results show that the proposed algorithm has better performance in randomness, stability and time overhead, which can effectively resist code reverse analysis.

17 December 2024 in arXiv
Verified
Preprint
Open access
PDF file
RNRuikang Ni
Ruikang Ni
DXDa Xiao
Da Xiao
QMQingye Meng
Qingye Meng
XLXiangyu Li
Xiangyu Li
SZShihui Zheng
Shihui Zheng
HLHongliang Liang
Hongliang Liang
Compositional relational reasoning (CRR) is a hallmark of human intelligence, but we lack a clear understanding of whether and how existing transformer large language models (LLMs) can solve CRR tasks. To enable systematic exploration of the CRR capability of LLMs, we first propose a new synthetic benchmark called Generalized Associative Recall (GAR) by integrating and generalizing the essence of several tasks in mechanistic interpretability (MI) study in a unified framework. Evaluation shows that GAR is challenging enough for existing LLMs, revealing their fundamental deficiency in CRR. Meanwhile, it is easy enough for systematic MI study. Then, to understand how LLMs solve GAR tasks, we use attribution patching to discover the core circuits reused by Vicuna-33B across different tasks and a set of vital attention heads. Intervention experiments show that the correct functioning of these heads significantly impacts task performance. Especially, we identify two classes of heads whose activations represent the abstract notion of true and false in GAR tasks respectively. They play a fundamental role in CRR across various models and tasks. The dataset and code are available at https://github.com/Caiyun-AI/GAR.