PulseAugur
EN
LIVE 06:45:37

New attack targets test-time adaptation models stealthily

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new method for sample-wise targeted adversarial attacks specifically designed for test-time adaptation (TTA) scenarios. This approach aims to misclassify only specific inputs containing an attacker-chosen trigger, while maintaining the overall label distribution of benign queries to evade detection. The proposed meta-learning-based attack utilizes a novel priority-aware gradient alignment strategy to optimize for attack success and distributional stealth simultaneously. AI

IMPACT This research highlights a new vulnerability in test-time adaptation, potentially influencing the development of more robust defense mechanisms.

RANK_REASON The cluster contains a research paper detailing a novel adversarial attack method.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Phuc Duc Nguyen, Quang Duc Nguyen ·

    Sample-wise Targeted Adversarial Attacks on Test-time Adaptation

    arXiv:2605.23411v1 Announce Type: new Abstract: Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Existing class-wise targeted attacks remain impractical for stealthy exploitation in t…

  2. arXiv cs.CV TIER_1 English(EN) · Quang Duc Nguyen ·

    Sample-wise Targeted Adversarial Attacks on Test-time Adaptation

    Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Existing class-wise targeted attacks remain impractical for stealthy exploitation in this setting: since TTA operates on batches, forc…

RELATED ENTITIES

RELATED TOPICS