Research map / Adversarial robustness and security / Certified and empirical robustness
On the Adversarial Vulnerability of Label-Free Test-Time Adaptation
Shahriar Rifat, Jonathan Ashdown, Michael J. De Lucia, Ananthram Swami, Francesco Restuccia
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Evaluates the adversarial vulnerability of label-free test-time adaptation methods under a threat model where attacks target the adaptation process itself.
Problem
Test-time adaptation (TTA) is vulnerable to small adversarial perturbations on test samples, and existing threat models may not capture the realistic risks for label-free TTA methods.
Approach
Argues that existing threat models assume test-time samples will be clean, and studies adversarial attacks on label-free TTA that exploit the adaptation mechanism; the abstract is truncated so the precise method is not fully stated.
Closest papers by meaning
- On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning (ICLR 2025 · similarity 0.94)
- Uncovering Adversarial Risks of Test-Time Adaptation (ICML 2023 · similarity 0.92)
- PTTA: Purifying Malicious Samples for Test-Time Model Adaptation (ICML 2025 · similarity 0.87)
- MedBN: Robust Test-Time Adaptation against Malicious Test Samples (CVPR 2024 · similarity 0.86)
- L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer (NeurIPS 2024 · similarity 0.85)
- Improved Generation of Adversarial Examples Against Safety-aligned LLMs (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
