Výsledky vyhledávání

Report

Towards Transferable Adversarial Attacks with Centralized Perturbation

Autor: Wu, Shangbo, Tan, Yu-an, Wang, Yajie, Ma, Ruinan, Ma, Wencong, Li, Yuanzhang

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image, resulting in ex

Externí odkaz: http://arxiv.org/abs/2312.06199

Zobrazit plný text záznamu

Report

Unified High-binding Watermark for Unconditional Image Generation Models

Autor: Ma, Ruinan, Tan, Yu-an, Wu, Shangbo, Chen, Tian, Wang, Yajie, Li, Yuanzhang

Deep learning techniques have implemented many unconditional image generation (UIG) models, such as GAN, Diffusion model, etc. The extremely realistic images (also known as AI-Generated Content, AIGC for short) produced by these models bring urgent n

Externí odkaz: http://arxiv.org/abs/2310.09479

Zobrazit plný text záznamu

Report

Concealed Electronic Countermeasures of Radar Signal with Adversarial Examples

Autor: Ma, Ruinan, Zhu, Canjie, Lu, Mingfeng, Li, Yunjie, Tan, Yu-an, Zhang, Ruibin, Tao, Ran

Electronic countermeasures involving radar signals are an important aspect of modern warfare. Traditional electronic countermeasures techniques typically add large-scale interference signals to ensure interference effects, which can lead to attacks b

Externí odkaz: http://arxiv.org/abs/2310.08292

Zobrazit plný text záznamu