arXiv subjects

Randolph Loh

Publications and source records attributed to Randolph Loh.

4 recordsLinked to original sources

arXiv2026

From Guidelines to Practice: Defining Requirements for AI Red-Teaming Tools

Artificial Intelligence (AI) has seen significant developments and increased usage in recent years. AI benefits various tasks, automates decision-making, and enhances efficiency. However, AI also introduces additional attack surfaces for threat actors to perform attacks like prompt injection and jailbreaking, making security a great concern. AI security testing aims to imitate adversarial attacks or malicious inputs via manual testing or with the assistance of tools. Thus, it is critical that organizations are aware of the capabilities and limitations of the tools before using them. Existing studies provide insights on the overall architecture of AI security testing tools and raise concerns on their reliability, but their analysis is limited to attack performance. Selection of a tool for AI risk assessments should also depend on their alignment with the recommendations of industry standards, but to our knowledge, previous studies have not utilized such guidelines. To bridge this gap, we analyze several industry standards and guidelines to identify the requirements of AI testing tools. We discuss and highlight desirable features across various AI security testing tools for a variety of different AI systems. We evaluated six tools across six Large Language Models, reported on our insights, and identified gaps that should be considered by future tools.

cs.CY↗

arXiv2024

Privacy preserving layer partitioning for Deep Neural Network models

MLaaS (Machine Learning as a Service) has become popular in the cloud computing domain, allowing users to leverage cloud resources for running private inference of ML models on their data. However, ensuring user input privacy and secure inference execution is essential. One of the approaches to protect data privacy and integrity is to use Trusted Execution Environments (TEEs) by enabling execution of programs in secure hardware enclave. Using TEEs can introduce significant performance overhead due to the additional layers of encryption, decryption, security and integrity checks. This can lead to slower inference times compared to running on unprotected hardware. In our work, we enhance the runtime performance of ML models by introducing layer partitioning technique and offloading computations to GPU. The technique comprises two distinct partitions: one executed within the TEE, and the other carried out using a GPU accelerator. Layer partitioning exposes intermediate feature maps in the clear which can lead to reconstruction attacks to recover the input. We conduct experiments to demonstrate the effectiveness of our approach in protecting against input reconstruction attacks developed using trained conditional Generative Adversarial Network(c-GAN). The evaluation is performed on widely used models such as VGG-16, ResNet-50, and EfficientNetB0, using two datasets: ImageNet for Image classification and TON IoT dataset for cybersecurity attack detection.

cs.CR↗

arXiv2023

Enhancing Cyber-Resilience in Self-Healing Cyber-Physical Systems with Implicit Guarantees

Self-Healing Cyber-Physical Systems (SH-CPS) effectively recover from system perceived failures without human intervention. They ensure a level of resilience and tolerance to unforeseen situations that arise from intrinsic system and component degradation, errors, or malicious attacks. Implicit redundancy can be exploited in SH-CPS to structurally adapt without the need to explicitly duplicate components. However, implicitly redundant components do not guarantee the same level of dependability as the primary component used to provide for a given function. Additional processes are needed to restore critical system functionalities as desired. This work introduces implicit guarantees to ensure the dependability of implicitly redundant components and processes. Implicit guarantees can be obtained through inheritance and decomposition. Therefore, a level of dependability can be guaranteed in SH-CPS after adaptation and recovery while complying with requirements. We demonstrate compliance with the requirement guarantees while ensuring resilience in SH-CPS.

cs.CR↗

arXiv2022

Data Privacy in Multi-Cloud: An Enhanced Data Fragmentation Framework

Data splitting preserves privacy by partitioning data into various fragments to be stored remotely and shared. It supports most data operations because data can be stored in clear as opposed to methods that rely on cryptography. However, majority of existing data splitting techniques do not consider data already in the multi-cloud. This leads to unnecessary use of resources to re-split data into fragments. This work proposes a data splitting framework that leverages on existing data in the multi-cloud. It improves data splitting mechanisms by reducing the number of splitting operations and resulting fragments. Therefore, decreasing the number of storage locations a data owner manages. Broadcasts queries locate third-party data fragments to avoid costly operations when splitting data. This work examines considerations for the use of third-party fragments and application to existing data splitting techniques. The proposed framework was also applied to an existing data splitting mechanism to complement its capabilities.

cs.CR↗