SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.07513 · 2022

Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to downstream tasks. Behind their revolutionary representation power, the requirements for dedicated model designs and a massive amount of computation resources expose image encoders to the risks of potential model stealing attacks - a cheap way to mimic the well-trained encoder performance while circumventing the demanding requirements. Yet conventional attacks only target supervised classifiers given their predicted labels and/or posteriors, which leaves the vulnerability of unsupervised encoders unexplored. In this paper, we first instantiate the conventional stealing attacks against encoders and demonstrate their severer vulnerability compared with downstream classifiers. To better leverage the rich representation of encoders, we further propose Cont-Steal, a contrastive-learning-based attack, and validate its improved stealing effectiveness in various experiment settings. As a takeaway, we appeal to our community's attention to the intellectual property protection of representation learning techniques, especially to the defenses against encoder stealing attacks like ours.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2201.07513")
get_code_for_paper("2201.07513")
have("2201.07513")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2201.07513.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2201.07513.svg)](https://syntology.ai/paper/2201.07513)

Connect an agent — have() is free.