19 papers
Correlation-Aware and Gaussianity-Preserving Robust Latent Angular Watermarking for Diffusion Models
Yebin Zheng, Haonan An, Guang Hua +2
Latent domain watermarking for diffusion models embeds watermarks directly into the latent prior, enjoying non-intrusiveness to model parameters and seamless integration with the g…
Universal Image Restoration via Internalized Chain-of-Thought Reasoning
Yu Guo, Zhengru Fang, Shengfeng He +4
Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations. While unified all-in-one models are comm…
FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
Yihang Tao, Yu Guo, Zhengru Fang +2
We present FRUC, a feedforward 3D Gaussian Splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing multi-agent reconstruction f…
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
Zhengru Fang, Yu Guo, Fei Liu +5
Real-world visual systems face time-varying perturbations, including weather, sensor noise, compression artifacts, and background distractions. Existing image restoration methods a…
CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
Zhengru Fang, Yanan Ma, Yu Guo +5
When a chest X-ray shows consolidation but the question asks which finding is present, a medical vision-language model may answer "No consolidation." This is more than an incorrect…
Inference-Time Budget Control for LLM Search Agents
Zhengru Fang, Senkang Forest Hu, Zhonghao Chang +6
LLM search agents increasingly rely on tools at inference time, but their trajectories are often constrained by hard limits on both tool calls and generated tokens. Under such dual…
Federated Mixture-of-Experts Alignment on Mobile Edge Networks under Data Heterogeneity
Zihan Fang, Qianru Wang, Haonan An +5
The growing demand for on-device large language model (LLM) services on mobile edge devices has driven the adoption of Mixture-of-Experts (MoE) architectures, which scale model cap…
RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces
Haonan An, Xiaohui Ye, Guang Hua +4
The proliferation of AI-generated content has facilitated sophisticated face manipulation, severely undermining visual integrity and posing unprecedented challenges to intellectual…
Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
Yihang Tao, Senkang Hu, Haonan An +3
Collaborative perception (CP) enables data sharing among connected and autonomous vehicles (CAVs) to enhance driving safety. However, CP systems are vulnerable to adversarial attac…
Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal
Haonan An, Guang Hua, Wei Du +5
Box-free model watermarking has gained significant attention in deep neural network (DNN) intellectual property protection due to its model-agnostic nature and its ability to flexi…
Shared Spatial Memory Through Predictive Coding
Zhengru Fang, Yu Guo, Yuang Zhang +3
Constructing a consistent shared spatial memory is a critical challenge in multi-agent systems, where partial observability and limited bandwidth often lead to catastrophic failure…
SAFE-D: A Spatiotemporal Detection Framework for Abnormal Driving Among Parkinson's Disease-like Drivers
Hangcheng Cao, Baixiang Huang, Longzhi Yuan +4
A driver's health state serves as a determinant factor in driving behavioral regulation. Subtle deviations from normalcy can lead to operational anomalies, posing risks to public t…
Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection
Yu Guo, Shengfeng He, Yuxu Lu +5
Maritime object detection is essential for navigation safety, surveillance, and autonomous operations, yet constrained by two key challenges: the scarcity of annotated maritime dat…
Distribution-Aligned Decoding for Efficient LLM Task Adaptation
Senkang Hu, Xudong Han, Jinqi Jiang +5
Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution…
Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
Haonan An, Guang Hua, Hangcheng Cao +4
The intellectual property of deep generative networks (GNets) can be protected using a cascaded hiding network (HNet) which embeds watermarks (or marks) into GNet outputs, known as…
NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling
Haonan An, Qianyao Ren, Guang Hua +5
Securing intellectual property (IP) in Machine Learning as a Service is critical yet challenging. While deep neural network watermarking serves as a standard defense against model…
Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
Haonan An, Guang Hua, Zhengru Fang +3
The intellectual property of deep image-to-image models can be protected by the so-called box-free watermarking. It uses an encoder and a decoder, respectively, to embed into and e…
GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection
Yihang Tao, Senkang Hu, Yue Hu +3
Collaborative perception significantly enhances autonomous driving safety by extending each vehicle's perception range through message sharing among connected and autonomous vehicl…
Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks
Haonan An, Guang Hua, Zhiping Lin +1
Box-free model watermarking is an emerging technique to safeguard the intellectual property of deep learning models, particularly those for low-level image processing tasks. Existi…