SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.11458 · 2024

Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness

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

Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily conservative training. As an alternative, we propose to model opponents as simply pursuing their own goals--rather than working directly against the classifier. Employing tools from strategic modeling, our approach enables knowledge or beliefs regarding the opponent's possible incentives to be used as inductive bias for learning. Accordingly, our method of strategic training is designed to defend against all opponents within an 'incentive uncertainty set'. This resorts to adversarial learning when the set is maximal, but offers potential gains when the set can be appropriately reduced. We conduct a series of experiments that show how even mild knowledge regarding the opponent's incentives can be useful, and that the degree of potential gains depends on how these incentives relate to the structure of the learning task.

For agents

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

get_harvested_code_for_paper("2406.11458")
get_code_for_paper("2406.11458")
have("2406.11458")

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

curl https://syntology.ai/api/ran/2406.11458.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.11458.svg)](https://syntology.ai/paper/2406.11458)

Connect an agent — have() is free.