CTI4AI: Threat Intelligence Generation and Sharing after Red Teaming AI Models

Authors: Chuyen Nguyen, Caleb Morgan, Sudip Mittal
Published: 2022-08-16

Source: https://arxiv.org/abs/2208.07476

PDF: https://arxiv.org/pdf/2208.07476

AIにより推定されたラベル

脆弱性検出 攻撃検出 AIシステムの関係性

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

As the practicality of Artificial Intelligence (AI) and Machine Learning (ML) based techniques grow, there is an ever increasing threat of adversarial attacks. There is a need to red team this ecosystem to identify system vulnerabilities, potential threats, characterize properties that will enhance system robustness, and encourage the creation of effective defenses. A secondary need is to share this AI security threat intelligence between different stakeholders like, model developers, users, and AI/ML security professionals. In this paper, we create and describe a prototype system CTI4AI, to overcome the need to methodically identify and share AI/ML specific vulnerabilities and threat intelligence.