98 citations · 172 across the 21 of their papers we have counts for
22 papers
Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models
Zhe Yu, Mohan Li, Lei Yu +6
Reasoning errors can propagate into later decisions and memory. This survey synthesizes 312 papers and first-party reports on text-based reasoning hallucinations around three quest…
On the Adversarial Robustness of Graph Neural Networks with Graph Reduction
Kerui Wu, Ka-Ho Chow, Wenqi Wei +1
As Graph Neural Networks (GNNs) become increasingly popular for learning from large-scale graph data across various domains, their susceptibility to adversarial attacks when using…
Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
Ka-Ho Chow, Sihao Hu, Tiansheng Huang +1
Face recognition (FR) can be abused for privacy intrusion. Governments, private companies, or even individual attackers can collect facial images by web scraping to build an FR sys…
Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning
Xueqing Zhang, Junkai Zhang, Ka-Ho Chow +6
This demo paper examines the susceptibility of Federated Learning (FL) systems to targeted data poisoning attacks, presenting a novel system for visualizing and mitigating such thr…
Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruning
Selim Furkan Tekin, Fatih Ilhan, Tiansheng Huang +4
This paper presents FusionShot, a focal diversity optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot m…
Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control
Ka-Ho Chow, Wenqi Wei, Lei Yu
Natural language processing (NLP) has received unprecedented attention. While advancements in NLP models have led to extensive research into their backdoor vulnerabilities, the pot…
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…
Atlas: Hybrid Cloud Migration Advisor for Interactive Microservices
Ka-Ho Chow, Umesh Deshpande, Veera Deenadhayalan +2
Hybrid cloud provides an attractive solution to microservices for better resource elasticity. A subset of application components can be offloaded from the on-premises cluster to th…
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…
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…
Promoting High Diversity Ensemble Learning with EnsembleBench
Yanzhao Wu, Ling Liu, Zhongwei Xie +3
Ensemble learning is gaining renewed interests in recent years. This paper presents EnsembleBench, a holistic framework for evaluating and recommending high diversity and high accu…
Understanding Object Detection Through An Adversarial Lens
Ka-Ho Chow, Ling Liu, Mehmet Emre Gursoy +3
Deep neural networks based object detection models have revolutionized computer vision and fueled the development of a wide range of visual recognition applications. However, recen…
LDP-Fed: Federated Learning with Local Differential Privacy
Stacey Truex, Ling Liu, Ka-Ho Chow +2
This paper presents LDP-Fed, a novel federated learning system with a formal privacy guarantee using local differential privacy (LDP). Existing LDP protocols are developed primaril…
A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
Wenqi Wei, Ling Liu, Margaret Loper +4
Federated learning (FL) is an emerging distributed machine learning framework for collaborative model training with a network of clients (edge devices). FL offers default client pr…
TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems
Ka-Ho Chow, Ling Liu, Mehmet Emre Gursoy +3
The rapid growth of real-time huge data capturing has pushed the deep learning and data analytic computing to the edge systems. Real-time object recognition on the edge is one of t…
Cross-Layer Strategic Ensemble Defense Against Adversarial Examples
Wenqi Wei, Ling Liu, Margaret Loper +4
Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adv…
Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness
Ling Liu, Wenqi Wei, Ka-Ho Chow +4
Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the en…
Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks
Ka-Ho Chow, Wenqi Wei, Yanzhao Wu +1
Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by add…
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
Yanzhao Wu, Ling Liu, Juhyun Bae +6
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs). Even for the baseline of a constant learning rate, it is non-trivi…
Representation Learning of Pedestrian Trajectories Using Actor-Critic Sequence-to-Sequence Autoencoder
Ka-Ho Chow, Anish Hiranandani, Yifeng Zhang +1
Representation learning of pedestrian trajectories transforms variable-length timestamp-coordinate tuples of a trajectory into a fixed-length vector representation that summarizes…