98 citations · 282 across the 36 of their papers we have counts for
37 papers
STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation
Nawrin Tabassum, Yanzhao Wu
Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two key challenges remain for existi…
What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models
Md Tasnim Jawad, Mingyan Xiao, Yanzhao Wu
With the widespread adoption of Large Language Models (LLMs) and increasingly stringent privacy regulations, protecting data privacy in LLMs has become essential, especially for pr…
Augmenting Question Answering with A Hybrid RAG Approach
Tianyi Yang, Nashrah Haque, Vaishnave Jonnalagadda +6
Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often…
Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models
Badhan Chandra Das, Md Tasnim Jawad, Joaquin Molto +2
In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research.…
A Diversity-optimized Deep Ensemble Approach for Accurate Plant Leaf Disease Detection
Sai Nath Chowdary Medikonduru, Hongpeng Jin, Yanzhao Wu
Plant diseases pose a significant threat to global agriculture, causing over $220 billion in annual economic losses and jeopardizing food security. The timely and accurate detectio…
Jailbreaking Large Vision Language Models in Intelligent Transportation Systems
Badhan Chandra Das, Md Tasnim Jawad, Md Jueal Mia +2
Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are…
System Prompt Extraction Attacks and Defenses in Large Language Models
Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles…
Accurate and Efficient Two-Stage Gun Detection in Video
Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
Object detection in videos plays a crucial role in advancing applications such as public safety and anomaly detection. Existing methods have explored different techniques, includin…
Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum
Nashrah Haque, Xiang Li, Zhehui Chen +4
We propose a novel framework, Stable Diffusion-based Momentum Integrated Adversarial Examples (SD-MIAE), for generating adversarial examples that can effectively mislead neural net…
In-depth Analysis of Privacy Threats in Federated Learning for Medical Data
Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
Federated learning is emerging as a promising machine learning technique in the medical field for analyzing medical images, as it is considered an effective method to safeguard sen…
On the Efficiency of Privacy Attacks in Federated Learning
Nawrin Tabassum, Ka-Ho Chow, Xuyu Wang +2
Recent studies have revealed severe privacy risks in federated learning, represented by Gradient Leakage Attacks. However, existing studies mainly aim at increasing the privacy att…
Security and Privacy Challenges of Large Language Models: A Survey
Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
Large Language Models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and que…
Hierarchical Pruning of Deep Ensembles with Focal Diversity
Yanzhao Wu, Ka-Ho Chow, Wenqi Wei +1
Deep neural network ensembles combine the wisdom of multiple deep neural networks to improve the generalizability and robustness over individual networks. It has gained increasing…
Privacy Risks Analysis and Mitigation in Federated Learning for Medical Images
Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
Federated learning (FL) is gaining increasing popularity in the medical domain for analyzing medical images, which is considered an effective technique to safeguard sensitive patie…
Invisible Watermarking for Audio Generation Diffusion Models
Xirong Cao, Xiang Li, Divyesh Jadav +4
Diffusion models have gained prominence in the image domain for their capabilities in data generation and transformation, achieving state-of-the-art performance in various tasks in…
Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness
Yanzhao Wu, Ka-Ho Chow, Wenqi Wei +1
Deep neural network ensembles hold the potential of improving generalization performance for complex learning tasks. This paper presents formal analysis and empirical evaluation to…
Rethinking Learning Rate Tuning in the Era of Large Language Models
Hongpeng Jin, Wenqi Wei, Xuyu Wang +2
Large Language Models (LLMs) represent the recent success of deep learning in achieving remarkable human-like predictive performance. It has become a mainstream strategy to leverag…
Fast and Resource-Efficient Object Tracking on Edge Devices: A Measurement Study
Sanjana Vijay Ganesh, Yanzhao Wu, Gaowen Liu +2
Object tracking is an important functionality of edge video analytic systems and services. Multi-object tracking (MOT) detects the moving objects and tracks their locations frame b…
Securing Distributed SGD against Gradient Leakage Threats
Wenqi Wei, Ling Liu, Jingya Zhou +2
This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First, we analyze two types of strategies for privacy-enhanced…
STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
Ka-Ho Chow, Ling Liu, Wenqi Wei +2
Federated Learning (FL) has been gaining popularity as a collaborative learning framework to train deep learning-based object detection models over a distributed population of clie…
Adaptive Deep Neural Network Inference Optimization with EENet
Fatih Ilhan, Ka-Ho Chow, Sihao Hu +9
Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test exampl…
Selecting and Composing Learning Rate Policies for Deep Neural Networks
Yanzhao Wu, Ling Liu
The choice of learning rate (LR) functions and policies has evolved from a simple fixed LR to the decaying LR and the cyclic LR, aiming to improve the accuracy and reduce the train…
Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering
Zhongwei Xie, Ling Liu, Yanzhao Wu +2
This paper introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineer…
Learning TFIDF Enhanced Joint Embedding for Recipe-Image Cross-Modal Retrieval Service
Zhongwei Xie, Ling Liu, Yanzhao Wu +2
It is widely acknowledged that learning joint embeddings of recipes with images is challenging due to the diverse composition and deformation of ingredients in cooking procedures.…