10 papers
SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
Zhaoxu Li, Chenqi Kong, Yi Yu +6
Large Vision-Language Models (LVLMs) recently achieve significant breakthroughs in understanding complex visual-textual contexts. However, hallucination issues still limit their re…
Covert Visual Prompt Injection against Commercial Multimodal Large Language Models
Meiwen Ding, Song Xia, Chenqi Kong +1
Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt inject…
Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture
Chenqi Kong, Anwei Luo, Peijun Bao +5
Open-set face forgery detection poses significant security threats and presents substantial challenges for existing detection models. These detectors primarily have two limitations…
Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization
Keyang Zhang, Chenqi Kong, Hui Liu +3
The increasing sophistication of image manipulation techniques demands robust forensic solutions that can both reliably detect alterations and precisely localize tampered regions.…
MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection
Chenqi Kong, Anwei Luo, Peijun Bao +5
Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expr…
ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack
Rongxuan Peng, Shunquan Tan, Chenqi Kong +3
Parameter-efficient fine-tuning (PEFT) has emerged as a popular strategy for adapting large vision foundation models, such as the Segment Anything Model (SAM) and LLaVA, to downstr…