AWAndrew Walenstein

Andrew Walenstein

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andrew Walenstein has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Obfuscated Clone Search in JavaScript based on Reinforcement Subsequence Learning

    by Leo Song, Steven H. H. Ding, Yuan Tian, Li Tao Li, Weihan Ou, Philippe Charland, Andrew Walenstein

    Finding similar code is important for software engineering, defense of intellectual property, and security, and one of the increasingly common ways adversaries use to defeat the detection of similar code is through obfuscations such as code transformation and scattering the code they wish to hide among long sequences. Moving code far enough apart poses a specific challenge for solutions with localized features (e.g., n-grams), or attention mechanisms as the code parts are distributed beyond the local context window. We introduce a neural network solution pattern called “Cybertron” that addresses this problem by utilizing reinforcement learning to train a code abstraction and summarization function; this converts arbitrarily long code into fixed-length real vectors in a way that is optimized for similarity search. The key to the design is the smart selection of important elements of the code and abstraction to preserve semantic function while minimizing syntactic feature information. We evaluated the approach on a three-challenge benchmark of obfuscated JavaScript, a scripting language that is commonly obfuscated and for which code-mixing is a rising challenge. The evaluation shows our approach identifies obfuscated code within even large scripts with an AUC of 78%, which outperforms current state-of-the-art sequence models by 7–35%.


  • Open Access

    Mecha: A Neural-Symbolic Open-Set Homogeneous Decision Fusion Approach for Zero-Day Malware Similarity Detection

    by Christopher Molloy, Jeremy Banks, Steven H. H. Ding, Furkan Alaca, Philippe Charland, Andrew Walenstein

    With increasing numbers of novel malware each year, tools are required for efficient and accurate variant matching under the same family, for the purpose of effective proactive threat detection, retro-hunting, and attack campaign tracking. All of the state-of-the-art Deep Learning (DL) approaches assume that the incoming samples originate from known families and incorrectly identify novel families. Additionally, most of the existing solutions that leverage the Siamese Neural Network architecture either rely on pair-wise comparisons or computationally expensive preprocessing steps that are not scalable to a real-world malware triage volume requirement. We propose a different route, Mecha, a Neural-Symbolic Machine Learning (ML) system for malware variant matching and zero-day family detection. Mecha is comprised of an embedding network trained in two different scenarios for byte string embedding and an open-set approximate nearest neighbour algorithm for variant matching and zero-day detection. Our embedding network uses triplet loss for embedding generation and reinforcement-based Expectation Maximization (EM) learning for full deployment optimization. We conduct multiple in-sample and out-of-sample experiments to demonstrate the model's generalizability toward novel variants and families. We also show that Mecha can detect samples outside the known set of malware samples with an accuracy greater than 0.990.


  • Open Access

    Dynamic Neural Control Flow Execution: an Agent-Based Deep Equilibrium Approach for Binary Vulnerability Detection

    by Litao Li, Steven H. H. Ding, Andrew Walenstein, Philippe Charland, Benjamin C. M. Fung

    Software vulnerabilities are a challenge in cybersecurity. Manual security patches are often difficult and slow to be deployed, while new vulnerabilities are created. Binary code vulnerability detection is less studied and more complex compared to source code, and this has important practical implications. Deep learning has become an efficient and powerful tool in the security domain, where it provides end-to-end and accurate prediction. Modern deep learning approaches learn the program semantics through sequence and graph neural networks, using various intermediate representation of programs, such as abstract syntax trees (AST) or control flow graphs (CFG). Due to the complex nature of program execution, the output of an execution depends on the many program states and inputs. Also, a CFG generated from static analysis can be an overestimation of the true program flow. Moreover, the size of programs often does not allow a graph neural network with fixed layers to aggregate global information. To address these issues, we propose DeepEXE, an agent-based implicit neural network that mimics the execution path of a program. We use reinforcement learning to enhance the branching decision at every program state transition and create a dynamic environment to learn the dependency between a vulnerability and certain program states. An implicitly defined neural network enables nearly infinite state transitions until convergence, which captures the structural information at a higher level. The experiments are conducted on two semi-synthetic and two real-world datasets. We show that DeepEXE is an accurate and efficient method and outperforms the state-of-the-art vulnerability detection methods.


  • Open Access

    Finding Associations between Natural and Computer Languages: A Case-Study of Bilingual Lda Applied to the Bleeping Computer Forum Posts

    by Kundi Yao, Gustavo Ansaldi Oliva, Ahmed E. Hassan, Muhammad Asaduzzaman, Andrew J. Malton, Andrew Walenstein

    In the context of technical support, trails of technical discussions often contain a mixture of natural language (e.g., English) and software log excerpts. Uncovering latent links between certain problems and log excerpts that are often requested during the discussions of those problems enables the construction of a valuable knowledge base. Nevertheless, uncovering such latent links is challenging because English and software logs are two fundamentally different languages. In this paper, we investigate the suitability of multilingual LDA models to address the problem at hand. We study three models: enriched LDA (M+), two-layer LDA (M_2L), and off-the-shelf bilingual LDA (M_bi). We evaluate them using three metrics: coherence, perplexity, and intercorpus ratio. We use approximately 8K discussion threads from a Bleeping Computer forum as our dataset. We observe that M_2L performs the best overall, while it yields a substantially coarser-grained view of the discussed themes in the threads (26 topics, 0.3% of the documents). M+ and M_bi perform similarly, with a higher coherence achieved by M+ and a lower perplexity achieved by M_bi. We invite future studies to qualitatively assess the quality of the topics produced by the LDA models, such that the feasibility of employing such models in practice is clarified.