https://martinuke0.github.io/tags/adversarial-ml/ Recent content in Adversarial-Ml on martinuke0's Blog https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E Hugo -- 0.152.2 en Wed, 02 Sep 2026 15:51:57 +0000 https://martinuke0.github.io/posts/2026-09-02-poisoning-attacks-on-llms-how-adversaries-corrupt-models-and-what-defenders-can-do/ Wed, 02 Sep 2026 15:51:57 +0000 https://martinuke0.github.io/posts/2026-09-02-poisoning-attacks-on-llms-how-adversaries-corrupt-models-and-what-defenders-can-do/ A practitioner's guide to data and model poisoning attacks on LLMs, with concrete defenses, real incidents, and an architecture for trustworthy training pipelines.