Source author record

Bhavani Thuraisingham

Bhavani Thuraisingham appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Machine Learning Cryptography and Security cs.CY Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Social and Information Networks

Catalog footprint

What is connected

6works

6topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

PEAR: Planner-Executor Agent Robustness Benchmark

Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse domains. However, despite their impressive capabilities, MAS remain susceptible to adversarial manipulation. Existing studies typically examine isolated attack surfaces or specific scenarios, leaving a lack of holistic understanding of MAS vulnerabilities. To bridge this gap, we introduce PEAR, a benchmark for systematically evaluating both the utility and vulnerability of planner-executor MAS. While compatible with various MAS architectures, our benchmark focuses on the planner-executor structure, which is a practical and widely adopted design. Through extensive experiments, we find that (1) a weak planner degrades overall clean task performance more severely than a weak executor; (2) while a memory module is essential for the planner, having a memory module for the executor does not impact the clean task performance; (3) there exists a trade-off between task performance and robustness; and (4) attacks targeting the planner are particularly effective at misleading the system. These findings offer actionable insights for enhancing the robustness of MAS and lay the groundwork for principled defenses in multi-agent settings.

preprint2026arXiv

Robust and Explainable Divide-and-Conquer Learning for Intrusion Detection

Machine learning-based intrusion detection requires complex models to capture patterns in high-dimensional, noisy, and class-imbalanced raw network traffic, yet deploying such models remains impractical on resource-constrained devices with limited processing power and memory. In this paper, we present a correlation-aware divide-and-conquer learning technique that decomposes a complex learning problem into smaller, more manageable subproblems. This enables lightweight models as simple as decision trees to be trained on focused subtasks, yielding up to 43.3% higher local accuracy and up to 257 times reduction in model size on real-world network intrusion detection datasets, while also improving adversarial robustness and explainability.

preprint2021arXiv

DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can inject poisoned samples into the datasets or embed backdoors in those models. Such an integrity breach can cause severe consequences, especially in safety- and security-critical applications. Various backdoor attack techniques have been proposed for higher effectiveness and stealthiness. Unfortunately, existing defense solutions are not practical to thwart those attacks in a comprehensive way. In this paper, we investigate the effectiveness of data augmentation techniques in mitigating backdoor attacks and enhancing DL models' robustness. An evaluation framework is introduced to achieve this goal. Specifically, we consider a unified defense solution, which (1) adopts a data augmentation policy to fine-tune the infected model and eliminate the effects of the embedded backdoor; (2) uses another augmentation policy to preprocess input samples and invalidate the triggers during inference. We propose a systematic approach to discover the optimal policies for defending against different backdoor attacks by comprehensively evaluating 71 state-of-the-art data augmentation functions. Extensive experiments show that our identified policy can effectively mitigate eight different kinds of backdoor attacks and outperform five existing defense methods. We envision this framework can be a good benchmark tool to advance future DNN backdoor studies.

preprint2020arXiv

COVID-19: The Information Warfare Paradigm Shift

In Kuhn's The Structure of Scientific Revolutions, the critical term is paradigm-shift when it suddenly becomes evident that earlier assumptions no longer are correct and the plurality of the scientific community that studies this domain accepts the change. These types of events can be scientific findings or as in social science system shock that creates a punctured equilibrium that sets the stage in the developments. In information warfare, recent years studies and government lines of efforts have been to engage fake news, electoral interference, and fight extremist social media as the primary combat theater in the information space, and the tools to influence a targeted audience. The COVID-19 pandemic generates a rebuttal of these assumptions. Even if fake news and extremist social media content may exploit fault lines in our society and create a civil disturbance, tensions between federal and local government, and massive protests, it is still effects that impact a part of the population. What we have seen with COVID-19, as an indicator, is that what is related to public health is far more powerful to swing public sentiment and create reactions within the citizenry that are trigger impact at a larger magnitude that has rippled through society in multiple directions.

preprint2011arXiv

Secure Data Processing in a Hybrid Cloud

Cloud computing has made it possible for a user to be able to select a computing service precisely when needed. However, certain factors such as security of data and regulatory issues will impact a user's choice of using such a service. A solution to these problems is the use of a hybrid cloud that combines a user's local computing capabilities (for mission- or organization-critical tasks) with a public cloud (for less influential tasks). We foresee three challenges that must be overcome before the adoption of a hybrid cloud approach: 1) data design: How to partition relations in a hybrid cloud? The solution to this problem must account for the sensitivity of attributes in a relation as well as the workload of a user; 2) data security: How to protect a user's data in a public cloud with encryption while enabling query processing over this encrypted data? and 3) query processing: How to execute queries efficiently over both, encrypted and unencrypted data? This paper addresses these challenges and incorporates their solutions into an add-on tool for a Hadoop and Hive based cloud computing infrastructure.

preprint2007arXiv

Toward Trusted Sharing of Network Packet Traces Using Anonymization: Single-Field Privacy/Analysis Tradeoffs

Network data needs to be shared for distributed security analysis. Anonymization of network data for sharing sets up a fundamental tradeoff between privacy protection versus security analysis capability. This privacy/analysis tradeoff has been acknowledged by many researchers but this is the first paper to provide empirical measurements to characterize the privacy/analysis tradeoff for an enterprise dataset. Specifically we perform anonymization options on single-fields within network packet traces and then make measurements using intrusion detection system alarms as a proxy for security analysis capability. Our results show: (1) two fields have a zero sum tradeoff (more privacy lessens security analysis and vice versa) and (2) eight fields have a more complex tradeoff (that is not zero sum) in which both privacy and analysis can both be simultaneously accomplished.