2024/04/12 by Yanting Wang, Wei Zou, Wang, Yanting +3 · 2 citations
Engineering · #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Hydraulic Fracturing and Reservoir Analysis
paper · pdf · doi:10.48550/arxiv.2404.08631
openalex publication_date 2024/04/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support samples) for a classification task. However, an attacker could perform data poisoning attacks by manipulating some support samples such that the classifier makes the attacker-desired, arbitrary prediction for a testing input. Empirical defenses cannot provide formal robustness guarantees, leading to a cat-and-mouse game between the attacker and defender. Existing certified defenses are designed for traditional supervised learning, resulting in sub-optimal performance when extended to few-shot classification. In our work, we propose FCert, the first certified defense against data poisoning attacks to few-shot classification. We show our FCert provably predicts the same label for a testing input under arbitrary data poisoning attacks when the total number of poisoned support samples is bounded. We perform extensive experiments on benchmark few-shot classification datasets with foundation models released by OpenAI, Meta, and Google in both vision and text domains. Our experimental results show our FCert: 1) maintains classification accuracy without attacks, 2) outperforms existing state-of-the-art certified defenses for data poisoning attacks, and 3) is efficient and general.