8 papers
MOBA: A Material-Oriented Backdoor Attack against LiDAR-based 3D Object Detection Systems
Saket S. Chaturvedi, Gaurav Bagwe, Lan Zhang +2
LiDAR-based 3D object detection is widely used in safety-critical systems. However, these systems remain vulnerable to backdoor attacks that embed hidden malicious behaviors during…
Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks
Gaurav Bagwe, Saket S. Chaturvedi, Xiaolong Ma +3
Retrieval-augmented generation (RAG) enhances factual grounding by integrating retrieval mechanisms with generative models but introduces new attack surfaces, particularly through…
Position: Human Factors Reshape Adversarial Analysis in Human-AI Decision-Making Systems
Shutong Fan, Lan Zhang, Xiaoyong Yuan
As Artificial Intelligence (AI) increasingly supports human decision-making, its vulnerability to adversarial attacks grows. However, the existing adversarial analysis predominantl…
DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
Jiaqi Liu, Lan Zhang, Xiaoyong Yuan
Text-to-image diffusion models (DMs) inadvertently reproduce copyrighted styles and protected visual concepts, raising legal and ethical concerns. Concept erasure has emerged as a…
AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt
Saket S. Chaturvedi, Gaurav Bagwe, Lan Zhang +1
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. How…
Sample-Efficient Reinforcement Learning Controller for Deep Brain Stimulation in Parkinson's Disease
Harsh Ravivarapu, Gaurav Bagwe, Xiaoyong Yuan +2
Deep brain stimulation (DBS) is an established intervention for Parkinson's disease (PD), but conventional open-loop systems lack adaptability, are energy-inefficient due to contin…