43 citations · 144 across the 27 of their papers we have counts for
27 papers
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…
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…
GPTs Window Shopping: An analysis of the Landscape of Custom ChatGPT Models
Benjamin Zi Hao Zhao, Muhammad Ikram, Mohamed Ali Kaafar
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 prom…
On mission Twitter Profiles: A Study of Selective Toxic Behavior
Hina Qayyum, Muhammad Ikram, Benjamin Zi Hao Zhao +3
The argument for persistent social media influence campaigns, often funded by malicious entities, is gaining traction. These entities utilize instrumented profiles to disseminate d…
Exploring the Distinctive Tweeting Patterns of Toxic Twitter Users
Hina Qayyum, Muhammad Ikram, Benjamin Zi Hao Zhao +3
In the pursuit of bolstering user safety, social media platforms deploy active moderation strategies, including content removal and user suspension. These measures target users eng…
Those Aren't Your Memories, They're Somebody Else's: Seeding Misinformation in Chat Bot Memories
Conor Atkins, Benjamin Zi Hao Zhao, Hassan Jameel Asghar +2
One of the new developments in chit-chat bots is a long-term memory mechanism that remembers information from past conversations for increasing engagement and consistency of respon…
A longitudinal study of the top 1% toxic Twitter profiles
Hina Qayyum, Benjamin Zi Hao Zhao, Ian D. Wood +3
Toxicity is endemic to online social networks including Twitter. It follows a Pareto like distribution where most of the toxicity is generated by a very small number of profiles an…
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…
A deep dive into the consistently toxic 1% of Twitter
Hina Qayyum, Benjamin Zi Hao Zhao, Ian D. Wood +3
Misbehavior in online social networks (OSN) is an ever-growing phenomenon. The research to date tends to focus on the deployment of machine learning to identify and classify types…
MANDERA: Malicious Node Detection in Federated Learning via Ranking
Wanchuang Zhu, Benjamin Zi Hao Zhao, Simon Luo +2
Byzantine attacks hinder the deployment of federated learning algorithms. Although we know that the benign gradients and Byzantine attacked gradients are distributed differently, t…
Hidden Backdoors in Human-Centric Language Models
Shaofeng Li, Hui Liu, Tian Dong +4
Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only…
On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models
Benjamin Zi Hao Zhao, Aviral Agrawal, Catisha Coburn +5
With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, priva…
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models
Liuqiao Chen, Hu Wang, Benjamin Zi Hao Zhao +2
Deep Neural Networks have achieved unprecedented success in the field of face recognition such that any individual can crawl the data of others from the Internet without their expl…
Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning
Benjamin Zi Hao Zhao, Mohamed Ali Kaafar, Nicolas Kourtellis
Data holders are increasingly seeking to protect their user's privacy, whilst still maximizing their ability to produce machine models with high quality predictions. In this work,…
Exploiting Behavioral Side-Channels in Observation Resilient Cognitive Authentication Schemes
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kaafar +2
Observation Resilient Authentication Schemes (ORAS) are a class of shared secret challenge-response identification schemes where a user mentally computes the response via a cogniti…
Deep Learning Backdoors
Shaofeng Li, Shiqing Ma, Minhui Xue +1
Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign in…
With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks and Defenses for Linear Regression Models
Jialin Wen, Benjamin Zi Hao Zhao, Minhui Xue +2
With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning,…
On the Resilience of Biometric Authentication Systems against Random Inputs
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kaafar
We assess the security of machine learning based biometric authentication systems against an attacker who submits uniform random inputs, either as feature vectors or raw inputs, in…
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…
On Inferring Training Data Attributes in Machine Learning Models
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Raghav Bhaskar +1
A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models. Further, the work of \ci…