Incident database / 2025-02-01

DeepSeek R1 showed 100% attack success rate in Cisco testing

Standard jailbreak suite (HarmBench)DeepSeek V3.2

Cisco's evaluation reported that DeepSeek R1 failed to block a single prompt from a 50-prompt HarmBench sample. Recorded against the DeepSeek family as the strongest public signal on its jailbreak posture; V3.2-specific retesting is pending our Phase 2 probe battery.

Sources

Sources (1)

Cisco security evaluation
Cisco security research · independent eval · source tier C · blogs.cisco.com · retrieved 2026-08-03

How to cite thisCC BY 4.0 — reuse freely, attribution required

Plain

ModelRiskIndex. "DeepSeek R1 showed 100% attack success rate in Cisco testing." Incident database, 2025-02-01. https://modelriskindex.com/incidents/deepseek-harmbench-2025

BibTeX

@misc{mri-2025-02-01,
  title  = {DeepSeek R1 showed 100% attack success rate in Cisco testing},
  author = {{ModelRiskIndex}},
  year   = {2025},
  note   = {Incident database, 2025-02-01},
  url    = {https://modelriskindex.com/incidents/deepseek-harmbench-2025}
}

Please cite the dated entry rather than the site root. Every assessment here is a point-in-time judgment bound to evidence retrieved on a specific date — an undated citation asserts something the data does not.

All incidents