12 citations · 29 across the 13 of their papers we have counts for
13 papers
Metaphor-based Jailbreak Attacks on Text-to-Image Models
Chenyu Zhang, Lanjun Wang, Yiwen Ma +3
Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversaria…
T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model
Chenyu Zhang, Tairen Zhang, Lanjun Wang +3
Using risky text prompts, such as pornography and violent prompts, to test the safety of text-to-image (T2I) models is a critical task. However, existing risky prompt datasets are…
Organ-Agents: Virtual Human Physiology Simulator via LLMs
Rihao Chang, He Jiao, Weizhi Nie +13
Recent advances in large language models (LLMs) have enabled new possibilities in simulating complex physiological systems. We introduce Organ-Agents, a multi-agent framework that…
Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning
Chenyu Zhang, Lanjun Wang, Yiwen Ma +2
Text-to-Image(T2I) models typically deploy safety filters to prevent the generation of sensitive images. Unfortunately, recent jailbreaking attack methods manually design instructi…
TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
Ruidong Chen, Honglin Guo, Lanjun Wang +3
Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, con…
Domain Adaptation from Generated Multi-Weather Images for Unsupervised Maritime Object Classification
Dan Song, Shumeng Huo, Wenhui Li +3
The classification and recognition of maritime objects are crucial for enhancing maritime safety, monitoring, and intelligent sea environment prediction. However, existing unsuperv…
Towards Deconfounded Image-Text Matching with Causal Inference
Wenhui Li, Xinqi Su, Dan Song +3
Prior image-text matching methods have shown remarkable performance on many benchmark datasets, but most of them overlook the bias in the dataset, which exists in intra-modal and i…
Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
Chenyu Zhang, Mingwang Hu, Wenhui Li +1
Recently, the text-to-image diffusion model has gained considerable attention from the community due to its exceptional image generation capability. A representative model, Stable…
MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining
Guokai Zhang, Lanjun Wang, Yuting Su +1
Today, the family of latent diffusion models (LDMs) has gained prominence for its high quality outputs and scalability. This has also raised security concerns on social media, as m…
Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks
Chenyu Zhang, Lanjun Wang, Anan Liu
Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing…
MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition
Dan Song, Xinwei Fu, Ning Liu +5
Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models f…
My Brother Helps Me: Node Injection Based Adversarial Attack on Social Bot Detection
Lanjun Wang, Xinran Qiao, Yanwei Xie +3
Social platforms such as Twitter are under siege from a multitude of fraudulent users. In response, social bot detection tasks have been developed to identify such fake users. Due…
T2IW: Joint Text to Image & Watermark Generation
An-An Liu, Guokai Zhang, Yuting Su +3
Recent developments in text-conditioned image generative models have revolutionized the production of realistic results. Unfortunately, this has also led to an increase in privacy…