Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness

Summary

This paper introduces Systemic Adversarial Robustness (SAR), a measure of how many distinct attacks are needed to compromise a pool of models that share training pipelines, distillation methods and data. Small SAR values indicate a vulnerability monoculture, while large values mean failures are spread across models. The authors formulate SAR as a partial set-cover problem with provable approximation guarantees, test it on vision and large language models, and report that model pools distilled from DeepSeek-R1 and Claude Opus 4.6 show lower estimated systemic robustness than their parent pools.

Topics

• Adversarial machine learning

Related items

• HighGHSA-46jr-4wx8-v453: MCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validationSame vendor · GitHub Advisory Database
• InfoBattle Drones - a vibe coded RTS with audio-based multiplayerSame vendor · Simon Willison's Weblog
• HighGHSA-22jm-h49p-29qw: MCP TypeScript SDK: Experimental tasks were not tied to the session that created themSame vendor · GitHub Advisory Database
• MediumGHSA-6prh-2h8m-c8cw: MCP TypeScript client SDK: HTTP client transports and OAuth requests followed cross-origin redirects and re-sent custom headers and request bodiesSame vendor · GitHub Advisory Database
• InfoAI in AppSec: What to Build vs. Buy | Endor LabsSame vendor · Endor Labs Blog