43 citations · 95 across the 24 of their papers we have counts for
29 papers
Beyond Model Scaling: Rethinking Sequence Construction for Transformer-based Network Intrusion Detection
Zeeshan Zulkifl Shah, Muhammad Ikram, Dali Kaafar +1
Transformer-based network intrusion detection systems (NIDS) have shown strong potential for detecting multi-stage cyberattacks, yet most methods construct input sequences using fi…
SpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy
Shashie Dilhara Batan Arachchige, Robin Carpentier, Hassan Jameel Asghar +1
User prompts provided to large language models (LLMs) may contain private information. One way to protect them is to execute the LLM inside a trusted execution environment (TEE). H…
Protecting User Prompts Via Character-Level Differential Privacy
Shashie Dilhara Batan Arachchige, Hassan Jameel Asghar, Benjamin Zi Hao Zhao +2
Large Language Models (LLMs) generate responses based on user prompts. Often, these prompts may contain highly sensitive information, including personally identifiable information…
DIALEVAL: Automated Type-Theoretic Evaluation of LLM Instruction Following
Nardine Basta, Dali Kaafar
Evaluating instruction following in Large Language Models requires decomposing instructions into verifiable requirements and assessing satisfaction--tasks currently dependent on ma…
CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs
Shashie Dilhara Batan Arachchige, Benjamin Zi Hao Zhao, Hassan Jameel Asghar +2
Large Language Models (LLMs) are often fine-tuned to adapt their general-purpose knowledge to specific tasks and domains such as cyber threat intelligence (CTI). Fine-tuning is mos…
Privacy-Preserving IoT in Connected Aircraft Cabin
Nilesh Vyas, Benjamin Zhao, Aygün Baltaci +6
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 th…
A Large-Scale Empirical Analysis of Custom GPTs' Vulnerabilities in the OpenAI Ecosystem
Sunday Oyinlola Ogundoyin, Muhammad Ikram, Hassan Jameel Asghar +2
Millions of users leverage generative pretrained transformer (GPT)-based language models developed by leading model providers for a wide range of tasks. To support enhanced user in…
Property-Preserving Hashing for -Distance Predicates: Applications to Countering Adversarial Input Attacks
Hassan Asghar, Chenhan Zhang, Dali Kaafar
Perceptual hashing is used to detect whether an input image is similar to a reference image with a variety of security applications. Recently, they have been shown to succumb to ad…
Bot Wars Evolved: Orchestrating Competing LLMs in a Counterstrike Against Phone Scams
Nardine Basta, Conor Atkins, Dali Kaafar
We present "Bot Wars," a framework using Large Language Models (LLMs) scam-baiters to counter phone scams through simulated adversarial dialogues. Our key contribution is a formal…
Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphs
Chenhan Zhang, Benjamin Zi Hao Zhao, Hassan Asghar +1
Users may inadvertently upload personally identifiable information (PII) to Machine Learning as a Service (MLaaS) providers. When users no longer want their PII on these services,…
-Privacy for Text and the Curse of Dimensionality
Hassan Jameel Asghar, Robin Carpentier, Benjamin Zi Hao Zhao +1
A widely used method to ensure privacy of unstructured text data is the multidimensional Laplace mechanism for -privacy, which is a relaxation of differential privacy for metr…
Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions
Robin Carpentier, Benjamin Zi Hao Zhao, Hassan Jameel Asghar +1
Interactions with online Large Language Models raise privacy issues where providers can gather sensitive information about users and their companies from the prompts. While textual…
Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption
Hassan Jameel Asghar, Zhigang Lu, Zhongrui Zhao +1
Two parties wish to collaborate on their datasets. However, before they reveal their datasets to each other, the parties want to have the guarantee that the collaboration would be…
Challenges with Passwordless FIDO2 in an Enterprise Setting: A Usability Study
Michal Kepkowski, Maciej Machulak, Ian Wood +1
Fast Identity Online 2 (FIDO2), a modern authentication protocol, is gaining popularity as a default strong authentication mechanism. It has been recognized as a leading candidate…
Fast IDentity Online with Anonymous Credentials (FIDO-AC)
Wei-Zhu Yeoh, Michal Kepkowski, Gunnar Heide +2
Web authentication is a critical component of today's Internet and the digital world we interact with. The FIDO2 protocol enables users to leverage common devices to easily authent…
On the Adversarial Inversion of Deep Biometric Representations
Gioacchino Tangari, Shreesh Keskar, Hassan Jameel Asghar +1
Biometric authentication service providers often claim that it is not possible to reverse-engineer a user's raw biometric sample, such as a fingerprint or a face image, from its ma…
DDoD: Dual Denial of Decision Attacks on Human-AI Teams
Benjamin Tag, Niels van Berkel, Sunny Verma +5
Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient. However, such systems are also at cons…
Use of Cryptography in Malware Obfuscation
Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Muhammad Ikram +4
Malware authors often use cryptographic tools such as XOR encryption and block ciphers like AES to obfuscate part of the malware to evade detection. Use of cryptography may give th…
Unintended Memorization and Timing Attacks in Named Entity Recognition Models
Rana Salal Ali, Benjamin Zi Hao Zhao, Hassan Jameel Asghar +3
Named entity recognition models (NER), are widely used for identifying named entities (e.g., individuals, locations, and other information) in text documents. Machine learning base…
Privacy Preserving Release of Mobile Sensor Data
Rahat Masood, Wing Yan Cheng, Dinusha Vatsalan +3
Sensors embedded in mobile smart devices can monitor users' activity with high accuracy to provide a variety of services to end-users ranging from precise geolocation, health monit…
Sharing in a Trustless World: Privacy-Preserving Data Analytics with Potentially Cheating Participants
Tham Nguyen, Hassan Jameel Asghar, Raghav Bhakar +2
Lack of trust between organisations and privacy concerns about their data are impediments to an otherwise potentially symbiotic joint data analysis. We propose DataRing, a data sha…
Data and Model Dependencies of Membership Inference Attack
Shakila Mahjabin Tonni, Dinusha Vatsalan, Farhad Farokhi +3
Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by obser…
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
Shaofeng Li, Minhui Xue, Benjamin Zi Hao Zhao +2
Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific in…
The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Services
Yuantian Miao, Minhui Xue, Chao Chen +5
With the rapid development of deep learning techniques, the popularity of voice services implemented on various Internet of Things (IoT) devices is ever increasing. In this paper,…