IEEE

Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation

Abstract: Recently, the adversarial vulnerability of deep neu ral networks (DNNs) has raised increasing attention. Among all the threat models, no-box attacks are the most practical but extremely ...
IEEE

Bounding Box Regression Network for Infrared Small Target Detection With Adaptive Receptive Field and Cross-Scale Fusion

Single-frame infrared small target (SIRST) detection is crucial for both military and civilian applications, but remains challenging due to low resolution and small target sizes. Most existing methods ...
GitHub

IDOL: Instant Photorealistic 3D Human Creation from a Single Image

Please refer to env/README.md for detailed environment setup instructions. dataset_root/ ├── deepfashion/ │ ├── image1/ │ │ ├── videos/ │ │ │ ├── xxx.mp4 │ │ │ └── xxx.jpg │ │ └── param ...
GitHub

JavaScript captcha solver (Node.js): Bypass reCAPTCHA, Cloudflare, GeeTest and more

Use the JavaScript captcha solver to automatically bypass any captcha - including reCAPTCHA v2, Invisible, v3, Enterprise, Cloudflare Turnstile, GeeTest sliders, Amazon WAF, FunCaptcha, and both image ...
Crypto Briefing

Yoland Yan: Comfy UI revolutionizes image generation with node-based precision, the ideogram model enhances control with bounding boxes, and granular prompting maximizes AI ...

Yoland Yan is the CEO of ComfyUI, the open-source AI workflow platform used by designers, VFX professionals, and studios to build and control generative AI workflows. He has led ComfyUI as it has ...