AI/ ai · security · computer-vision · adversarial-ml

AEGIS Framework Spots Adversarial Attacks on Vision AI

A new detection system combining semantic analysis and uncertainty modeling catches six categories of adversarial image attacks with over 90% accuracy.

A research framework called AEGIS claims to catch adversarial image attacks before they fool vision AI systems — and it does it without relying on the overconfident probability scores that trip up most existing detectors.

The framework, detailed in a new paper, works in two stages. First, a module called SemantiGAN acts as a semantic discriminator, screening images for visual inconsistencies before they travel further down the pipeline. Images that clear that filter get put through stochastic augmentation — randomized tweaks that expose instability — and five metrics are computed from the results: FlipScore, Prediction Inconsistency, Layerwise Cosine Similarity at early and mid layers, and Entropy. Those five values feed an Evidential Deep Learning classifier that models uncertainty using a Dirichlet distribution, yielding not just a prediction but a calibrated confidence estimate. Tested against six attack types on Tiny ImageNet — including FGSM, PGD, patch-based, functional, and geometric attacks — AEGIS hit an AUROC of 92.1%, an AUPRC of 90.2%, and an accuracy of 90.7%.

The calibrated uncertainty piece matters more than the headline numbers. Most adversarial detectors use softmax outputs, which are notoriously overconfident — a network can assign 99% probability to a wrong answer and never flag it as suspicious. By modeling evidence distributions instead, AEGIS can say "I don't know" rather than commit to a confident wrong guess, which is exactly the behavior you want in a security-critical pipeline.

Adversarial robustness research has been promising dramatic fixes for years; the real test for AEGIS, as with every paper in this space, is whether the gains hold against adaptive attackers who know the detector exists.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →