Benjamin Zi Hao Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Benjamin Zi Hao Zhao has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Hassan Jameel Asghar
School of Computing, Macquarie University, Sydney, NSW, Australia
11 shared publications Dali Kaafar
School of Computing, Macquarie University, Sydney, NSW, Australia
8 shared publications- Mohamed Ali Kaafar
Macquarie University
8 shared publications - Muhammad Ikram
Macquarie University Sydney Australia
8 shared publications - Ian David Wood
Macquarie University
3 shared publications - Dinusha Vatsalan
Macquarie University
2 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 363-374
Protecting User Prompts Via Character-Level Differential Privacy
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 363-374
Open AccessProtecting User Prompts Via Character-Level Differential Privacy
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 913-923
Forget Me, Not My Friends! Object Unlearning Based on Scene Graphs
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 913-923
Open AccessForget Me, Not My Friends! Object Unlearning Based on Scene Graphs
- Open Access
- 1 January 2026
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2026 (1) , 224-241
dX-Privacy for Text and the Curse of Dimensionality
A widely used method to ensure privacy of unstructured text data is the multidimensional Laplace mechanism for dX-privacy, which is a relaxation of differential privacy for metric spaces. We identify an intriguing peculiarity of this mechanism. When applied on a word-by-word basis, the mechanism either outputs the original word, or completely dissimilar words, and very rarely outputs semantically similar words. We investigate this observation in detail, and tie it to the fact that the distance of the nearest neighbor of a word in any word embedding model (which are high-dimensional) is much larger than the relative difference in distances to any of its two consecutive neighbors. We also show that the dot product of the multidimensional Laplace noise vector with any word embedding plays a crucial role in designating the nearest neighbor. We derive the distribution, moments and tail bounds of this dot product. We further propose a fix as a post-processing step, which satisfactorily removes the above-mentioned issue.
- 1 January 2026
- Published by Privacy Enhancing Technologies Symposium Advisory Board in Proceedings on Privacy Enhancing Technologies
- Vol. 2026 (1) , 224-241
Open AccessdX-Privacy for Text and the Curse of Dimensionality
A widely used method to ensure privacy of unstructured text data is the multidimensional Laplace mechanism for dX-privacy, which is a relaxation of differential privacy for metric spaces. We identify an intriguing peculiarity of this mechanism. When applied on a word-by-word basis, the mechanism either outputs the original word, or completely dissimilar words, and very rarely outputs semantically similar words. We investigate this observation in detail, and tie it to the fact that the distance of the nearest neighbor of a word in any word embedding model (which are high-dimensional) is much larger than the relative difference in distances to any of its two consecutive neighbors. We also show that the dot product of the multidimensional Laplace noise vector with any word embedding plays a crucial role in designating the nearest neighbor. We derive the distribution, moments and tail bounds of this dot product. We further propose a fix as a post-processing step, which satisfactorily removes the above-mentioned issue.
- Open Access
Privacy-Preserving IoT in Connected Aircraft Cabin
The proliferation of IoT devices in shared, multi-vendor environments like the modern aircraft cabin creates a fundamental conflict between the promise of data collaboration and the risks to passenger privacy, vendor intellectual property (IP), and regulatory compliance. While emerging standards like the Cabin Secure Media-Independent Messaging (CSMIM) protocol provide a secure communication backbone, they do not resolve data governance challenges at the application layer, leaving a privacy gap that impedes trust. This paper proposes and evaluates a framework that closes this gap by integrating a configurable layer of Privacy-Enhancing Technologies (PETs) atop a CSMIM-like architecture. We conduct a rigorous, empirical analysis of two pragmatic PETs: Differential Privacy (DP) for statistical sharing, and an additive secret sharing scheme (ASS) for data obfuscation. Using a high-fidelity testbed with resource-constrained hardware, we quantify the trade-offs between data privacy, utility, and computing performance. Our results demonstrate that the computational overhead of PETs is often negligible compared to inherent network and protocol latencies. We prove that architectural choices, such as on-device versus virtualized processing, have a far greater impact on end-to-end latency and computational performance than the PETs themselves. The findings provide a practical roadmap for system architects to select and configure appropriate PETs, enabling the design of trustworthy collaborative IoT ecosystems in avionics and other critical domains.
Open AccessPrivacy-Preserving IoT in Connected Aircraft Cabin
The proliferation of IoT devices in shared, multi-vendor environments like the modern aircraft cabin creates a fundamental conflict between the promise of data collaboration and the risks to passenger privacy, vendor intellectual property (IP), and regulatory compliance. While emerging standards like the Cabin Secure Media-Independent Messaging (CSMIM) protocol provide a secure communication backbone, they do not resolve data governance challenges at the application layer, leaving a privacy gap that impedes trust. This paper proposes and evaluates a framework that closes this gap by integrating a configurable layer of Privacy-Enhancing Technologies (PETs) atop a CSMIM-like architecture. We conduct a rigorous, empirical analysis of two pragmatic PETs: Differential Privacy (DP) for statistical sharing, and an additive secret sharing scheme (ASS) for data obfuscation. Using a high-fidelity testbed with resource-constrained hardware, we quantify the trade-offs between data privacy, utility, and computing performance. Our results demonstrate that the computational overhead of PETs is often negligible compared to inherent network and protocol latencies. We prove that architectural choices, such as on-device versus virtualized processing, have a far greater impact on end-to-end latency and computational performance than the PETs themselves. The findings provide a practical roadmap for system architects to select and configure appropriate PETs, enabling the design of trustworthy collaborative IoT ecosystems in avionics and other critical domains.
- Open Access
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 147-161
Unsafe by Design? A First Look at Security and Privacy Risks in OpenAI’s Custom GPT Ecosystem
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 147-161
Open AccessUnsafe by Design? A First Look at Security and Privacy Risks in OpenAI’s Custom GPT Ecosystem
- 16 May 2025
- Published by Springer Nature
- p. 61-75
Facing the Challenge of Leveraging Untrained Humans in Malware Analysis
- 16 May 2025
- Published by Springer Nature
- p. 61-75
Facing the Challenge of Leveraging Untrained Humans in Malware Analysis
- 1 April 2025
- Published by Springer Nature
- p. 149-170
On the Robustness of Malware Detectors to Adversarial Samples
- 1 April 2025
- Published by Springer Nature
- p. 149-170
On the Robustness of Malware Detectors to Adversarial Samples
- 14 March 2025
- Published by Springer Nature
- p. 82-106
PPDL: Efficient Dropout-Resilient Aggregation for Privacy-Preserving Decentralized Learning
- 14 March 2025
- Published by Springer Nature
- p. 82-106
PPDL: Efficient Dropout-Resilient Aggregation for Privacy-Preserving Decentralized Learning
- 27 November 2024
- Published by Springer Nature
- p. 116-132
On Adversarial Training with Incorrect Labels
- Open Access
GPTs Window Shopping: An analysis of the Landscape of Custom ChatGPT Models
OpenAI's ChatGPT initiated a wave of technical iterations in the space of Large Language Models (LLMs) by demonstrating the capability and disruptive power of LLMs. OpenAI has prompted large organizations to respond with their own advancements and models to push the LLM performance envelope. OpenAI has prompted large organizations to respond with their own advancements and models to push the LLM performance envelope. OpenAI's success in spotlighting AI can be partially attributed to decreased barriers to entry, enabling any individual with an internet-enabled device to interact with LLMs. What was previously relegated to a few researchers and developers with necessary computing resources is now available to all. A desire to customize LLMs to better accommodate individual needs prompted OpenAI's creation of the GPT Store, a central platform where users can create and share custom GPT models. Customization comes in the form of prompt-tuning, analysis of reference resources, browsing, and external API interactions, alongside a promise of revenue sharing for created custom GPTs. In this work, we peer into the window of the GPT Store and measure its impact. Our analysis constitutes a large-scale overview of the store exploring community perception, GPT details, and the GPT authors, in addition to a deep-dive into a 3rd party storefront indexing user-submitted GPTs, exploring if creators seek to monetize their creations in the absence of OpenAI's revenue sharing.
Open AccessGPTs Window Shopping: An analysis of the Landscape of Custom ChatGPT Models
OpenAI's ChatGPT initiated a wave of technical iterations in the space of Large Language Models (LLMs) by demonstrating the capability and disruptive power of LLMs. OpenAI has prompted large organizations to respond with their own advancements and models to push the LLM performance envelope. OpenAI has prompted large organizations to respond with their own advancements and models to push the LLM performance envelope. OpenAI's success in spotlighting AI can be partially attributed to decreased barriers to entry, enabling any individual with an internet-enabled device to interact with LLMs. What was previously relegated to a few researchers and developers with necessary computing resources is now available to all. A desire to customize LLMs to better accommodate individual needs prompted OpenAI's creation of the GPT Store, a central platform where users can create and share custom GPT models. Customization comes in the form of prompt-tuning, analysis of reference resources, browsing, and external API interactions, alongside a promise of revenue sharing for created custom GPTs. In this work, we peer into the window of the GPT Store and measure its impact. Our analysis constitutes a large-scale overview of the store exploring community perception, GPT details, and the GPT authors, in addition to a deep-dive into a 3rd party storefront indexing user-submitted GPTs, exploring if creators seek to monetize their creations in the absence of OpenAI's revenue sharing.