# New Papers Automate Multimodal Jailbreak Discovery and Map Frontier AI Risk in Critical Infrastructure

One method breaks jailbreaks into atomic strategies and recombines them to generate attacks automatically. A companion paper argues that frontier systems change infrastructure risk at the system level rather than the component level.

- Published: 2026-08-06T05:47:01.202Z
- Canonical: https://polylog.news/ai/2026-08-06/new-papers-automate-multimodal-jailbreak-discovery-and-map-f
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CR](https://arxiv.org/abs/2608.04034), [arXiv cs.CR](https://arxiv.org/abs/2608.04033), [Anthropic Frontier Red Team](https://www.anthropic.com/research/team/frontier-red-team)

Two security papers posted to arXiv this morning approach the same gap from different directions. Capability is measured continuously, while the safety properties of deployed systems are still assessed by hand. The first proposes an automat…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-06/new-papers-automate-multimodal-jailbreak-discovery-and-map-f (subscription information: https://polylog.news/pricing).