↓Skip to main content

Public Exposure

2025

Adversarial Testing of AI is not Optional

··1648 words·8 mins

by: Satu Korhonen and Silvan Gebhardt

AI systems fail in unpredictable ways, from suggesting insecure code to leaking sensitive data. Learn why traditional security testing isn't enough and why adversarial testing is essential to understanding and mitigating the real risks of generative AI.
AI systems fail in unpredictable ways, from suggesting insecure code to leaking sensitive data. Learn why traditional security testing isn’t enough and why adversarial testing is essential to understanding and mitigating the real risks of generative AI.

2024

2023

2022

Practical Methods for Assessing Your External Attack Surface

··2309 words·11 mins

by: Juhani Eronen

The siege of Château Gaillard between September 1203 and March 1204 is a good example of determined attackers exploiting a weakness in the defenders' threat model. As the story has it, a French soldier clambered up the latrine chute and let in his compatriots to take over the castle. Photo (c) Lari Huttunen.
The siege of Château Gaillard between September 1203 and March 1204 is a good example of determined attackers exploiting a weakness in the defenders’ threat model. As the story has it, a French soldier clambered up the latrine chute and let in his compatriots to take over the castle.