A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency

1 code implementation • 3 May 2025 • Sihyeong Park, Sungryeol Jeon, Chaelyn Lee, Seokhun Jeon, Byung-soo Kim, Jemin Lee

This paper provides a comprehensive evaluation of 25 open-source and commercial inference engines.

BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks

1 code implementation • 6 Feb 2025 • Hanyong Lee, Chaelyn Lee, YongJae lee, Jaesung Lee

We release the BitAbuse dataset, which includes real-world phishing cases annotated with visual perturbations, to support future research in adversarial attack defense.

Adversarial Attack