4 citations · 7 across the 14 of their papers we have counts for
8 papers · 1 filter
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…
RobotArena : Scalable Robot Benchmarking via Real-to-Sim Translation
Yash Jangir, Yidi Zhang, Pang-Chi Lo +7
The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot…
Are Targeted Data Poisoning Attacks as Effective as We Think?
William Xu, Chenyu Zhang, Yihan Wang +5
Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack succ…
Adaptive Physics-Informed System Modeling with Control for Nonlinear Structural System Estimation
Biqi Chen, Chenyu Zhang, Jun Zhang +1
Accurately capturing the nonlinear dynamic behavior of structures remains a significant challenge in mechanics and engineering. Traditional physics-based models and data-driven app…
SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
Chenyu Zhang, Kunlun Xu, Zichen Liu +2
Vision-language models (VLMs) encounter considerable challenges when adapting to domain shifts stemming from changes in data distribution. Test-time adaptation (TTA) has emerged as…
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…