Qing Guo

Full Professor@Nankai University·中国·OpenReview

研究方向

Computer vision · AI security · Adversarial attack and defense · DeepFake detection and generation · Computer vision on image denoising · segmentation · and visual object tracking

Qing Guo

Probabilistic Robustness for Free? Revisiting Training via a Benchmark

Beyond Visual Reconstruction Quality: Object Perception-aware 3D Gaussian Splatting for Autonomous Driving

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFake

Severing the Link: A Unified Adversarial Attack on Image and Video MLLMs via Generative Disruption

A Diffusion-based Foundation Model for Irregular Spatio-Temporal Trajectories

OBJVANISH: PHYSICALLY REALIZABLE TEXT-TO-3D ADV. GENERATION OF LIDAR-INVISIBLE OBJECTS

PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference

PersonBias: A Lightweight Framework for Personalized Bias Mitigation in Large Language Models

Few-Shot Idea Auto-Generation: Reasoning Over Idea Representations to Predict New Research Ideas

Value-Alignment via Safe Semantic Manifold-Constrained Latent Diffusion

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions

Fair-SP: Capturing Pluralistic Social Equity Preferences Through Synthetic Data

LLM-STAR: Sequence-Teacher-Anchored LLM Recommender with Adaptive Regularization

Mask Image Watermarking

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

Open-Vocabulary Part Segmentation via Progressive and Boundary-Aware Strategy

AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking

EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation

Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning

Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models

Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision

MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling

Beautifying Diffusion Models: Learning Context-Aware Filters for Robust Dense Prediction on Test-Time Corrupted Images

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems

Quality Diversity Imitation Learning

Time-variant Duo-image Inpainting via Interactive Distribution Transition Estimation

CamoVid60K: A Large-Scale Video Dataset for Moving Camouflaged Animals Understanding

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution

Defend against Jailbreak Attacks via Debate with Partially Perceptive Agents

CRVR: Continuous Representation-Driven Video Frame Modulation Against rPPG Heart Rate Measurement