10 citations · 16 across the 30 of their papers we have counts for
21 papers · 1 filter
Answer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models
Shunyuan Bai, Yuchen Ren, Le Yang +3
With the advancement in language modeling, research on adversarial images has recently shifted from image classifiers to vision-language models (VLMs). Despite the new, text-prompt…
Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video Continuation
Yingmao Miao, Pengfei Zhang, Chaoran Xu +5
Video generators build long videos by composing shorter parts, either by generating segments one after another or by autoregressively extending chunks. Each new part usually depend…
Detecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification
Xuanbing Wen, Boxu Chen, Le Yang +4
Despite recent advances in large vision-language models (LVLMs), object hallucination remains a major barrier to their reliable deployment. Existing detection methods often charact…
Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift
Longtian Wang, Zhengyu Zhao, Chenhao Lin +5
Object detection models deployed in safety-critical applications remain vulnerable to backdoor attacks that cause targeted misbehaviors when a hidden trigger is present. Existing d…
Evaluation-Verification Reward for Consistent Multi-Reference Image Editing
Yingmao Miao, Pengfei Zhang, Xiaochen Lv +5
While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency across references and ensuri…
On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline
Yuchen Ren, Zhengyu Zhao, Chenhao Lin +2
Vision-Language Pre-training Models (VLPMs) are known to be vulnerable to adversarial attacks. Recent transferable attacks on VLPMs have followed a common pipeline with complicated…
CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection
Hang Wang, Chao Shen, Chenhao Lin +3
The proliferation of advanced AI video synthesis techniques poses an unprecedented challenge to digital video authenticity. Existing AI-generated video (AIGV) detection methods pri…
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
Ye Leng, Junjie Chu, Mingjie Li +5
Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much strong…
Multi-modal Deepfake Detection and Localization with FPN-Transformer
Chende Zheng, Ruiqi Suo, Zhoulin Ji +4
The rapid advancement of generative adversarial networks (GANs) and diffusion models has enabled the creation of highly realistic deepfake content, posing significant threats to di…
Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights
Junhao Zheng, Jiahao Sun, Chenhao Lin +6
Developing reliable defenses against patch attacks on object detectors has attracted increasing interest. However, we identify that existing defense evaluations lack a unified and…
D3: Training-Free AI-Generated Video Detection Using Second-Order Features
Chende Zheng, Ruiqi suo, Chenhao Lin +6
The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the disseminatio…
Adversarial Video Promotion Against Text-to-Video Retrieval
Qiwei Tian, Chenhao Lin, Zhengyu Zhao +3
Thanks to the development of cross-modal models, text-to-video retrieval (T2VR) is advancing rapidly, but its robustness remains largely unexamined. Existing attacks against T2VR a…
Concept Unlearning by Modeling Key Steps of Diffusion Process
Chaoshuo Zhang, Chenhao Lin, Zhengyu Zhao +3
Text-to-image diffusion models remain susceptible to generating undesirable or harmful content. Although concept unlearning mitigates this risk, existing methods struggle with a cr…
Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations
Boxu Chen, Ziwei Zheng, Le Yang +4
Large Vision-Language Models (LVLMs) have achieved remarkable success but continue to struggle with object hallucination (OH), generating outputs inconsistent with visual inputs. W…
HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation
Hang Wang, Zhi-Qi Cheng, Chenhao Lin +2
Text-to-image synthesis has progressed to the point where models can generate visually compelling images from natural language prompts. Yet, existing methods often fail to reconcil…
Use as Many Surrogates as You Want: Selective Ensemble Attack to Unleash Transferability without Sacrificing Resource Efficiency
Bo Yang, Hengwei Zhang, Jindong Wang +4
In surrogate ensemble attacks, using more surrogate models yields higher transferability but lower resource efficiency. This practical trade-off between transferability and efficie…
ID-Booth: Identity-consistent Face Generation with Diffusion Models
Darian Tomašević, Fadi Boutros, Chenhao Lin +3
Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition. Here, stat…
Shining Yourself: High-Fidelity Ornaments Virtual Try-on with Diffusion Model
Yingmao Miao, Zhanpeng Huang, Rui Han +3
While virtual try-on for clothes and shoes with diffusion models has gained attraction, virtual try-on for ornaments, such as bracelets, rings, earrings, and necklaces, remains lar…
Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
Yuchen Ren, Zhengyu Zhao, Chenhao Lin +4
Vision Transformers (ViTs) have been widely applied in various computer vision and vision-language tasks. To gain insights into their robustness in practical scenarios, transferabl…
Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
Le Yang, Ziwei Zheng, Boxu Chen +3
Recent studies have shown that large vision-language models (LVLMs) often suffer from the issue of object hallucinations (OH). To mitigate this issue, we introduce an efficient met…
Generalizable Targeted Data Poisoning against Varying Physical Objects
Zhizhen Chen, Zhengyu Zhao, Subrat Kishore Dutta +3
Targeted data poisoning (TDP) aims to compromise the model's prediction on a specific (test) target by perturbing a small subset of training data. Existing work on TDP has focused…