Nov 27, 2025 · 5 min read · In this post, I want to share some threat hunting techniques I’ve honed over time while investigating adversary infrastructure using crowdsourced and freemium tools. While enterprise tools are powerful, you don't always need a massive budget to find ...
Join discussion
Nov 21, 2025 · 7 min read · The alert goes off at 2:17 p.m. You count yourself lucky that this one’s in the afternoon, not morning. You drop what you’re doing, open the console, and start digging in. Oh, a significant spike in outbound traffic from a Kubernetes node. A privileg...
Join discussion
Jul 29, 2025 · 10 min read · Exploring adversarial attacks - where tiny, imperceptible modifications can completely deceive even the smartest neural networks From Autoencoders to Adversarial Attacks: A New Kind of Magic After my fascinating journey with Variational Autoencoders,...
Join discussionMay 24, 2025 · 5 min read · 🔍 What Are Adversarial Examples? Adversarial examples are inputs that have been slightly modified to fool a model into making a wrong prediction, even though the change is imperceptible to humans. Given an input image, we generate an adversarial ex...
Join discussion
May 19, 2025 · 2 min read · Adversarial testing is a method of testing systems—especially AI models, software, or security mechanisms—by intentionally trying to break them, fool them, or find their weaknesses using carefully crafted inputs called adversarial examples. As we con...
Join discussionDec 5, 2024 · 4 min read · Intro The rise of highly capable AI systems has brought immense opportunities alongside critical challenges. Ensuring that these systems are reliable, transparent, and aligned with human values has become a pivotal area of research. This blog delves ...
Join discussion
Nov 7, 2024 · 7 min read · 👋 Introduction Machine learning models in the present day use gigantic amounts of training data to train them. Be it LLMs or NLPs, they have to be constantly trained to tackle real-world problems. These models are so complex that it is difficult for...
Join discussion
Sep 2, 2020 · 2 min read · paper link: https://dl.acm.org/doi/pdf/10.1145/3366423.3380171?casa_token=N5jr2JHp3KMAAAAA:2BcySv_APTzji9nikXSFJhWvVbr8xkyFKCqdcESwZxHV9waZPP0MMec-RmSZJzi-WGsRmuJzqet9 Published in KDD 2020 此篇為這issue的第一篇paper，故提出的方法實驗效果並沒有很好，只是題目新穎能帶來啟發 前言 Community ...
Join discussion