threatdeck
Live 13:45 UTC ·

MITRE ATLAS · AI Attack Adaptation

AML.T0043 · Craft Adversarial Data

Adversarial data are inputs to an AI model that have been modified such that they cause the adversary's desired effect in the target model. Effects can range from misclassification, to missed detections, to maximizing energy consumption. Typically, the modification is constrained in magnitude or location so that a human still perceives the data as if it were unmodified, but human perceptibility ma

MITRE ATLAS

Mitigations

  • Predictive AI Output Obfuscation
  • Predictive AI Model Hardening
  • Limit AI Service Query Volume and Rate
  • Predictive AI Ensembles
  • Predictive AI Input Restoration
  • Predictive AI Adversarial Input Detection

In the news

  1. Attacks on AI Research arXiv (AI security papers) Medium

    A Wolf in Sheep's Pixels: Visual Camouflage Attacks via HDR Gain Maps

    DRJanus is a visual camouflage attack that embeds a harmful image in a JPEG's HDR gain map, evading automated checks that read only the SDR base image.

    ReviewReview image moderation pipelines that rely only on SDR image content

    AML.T0043 arXiv:2611.25469 #content-moderation#jpeg#adversarial-images 1 min read Brief In your stack

Tools

Test or exercise it

Detect or mitigate it

Mappings are AI-assisted and checked against the framework definitions; corrections welcome.

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.