DeepSeek v3.1 — Cyber Threats, Attacks & Incidents

Threat entity extracted from intelligence sources

Frequency
2
occurrences
First Seen
November 7, 2025
Last Seen
November 21, 2025

DeepSeek v3.1 is a technology platform tracked across 2 threat clusters and 2 intelligence report mentions on ThreatCluster. First observed November 7, 2025; most recent activity November 21, 2025.

Overview

DeepSeek v3.1 is a technology platform referenced in Cisco's analysis of large language model (LLM) vulnerabilities. The article implies that platforms leveraging LLMs, such as DeepSeek v3.1, may be exposed to iterative attacks that can undermine model safeguards and data integrity, making it a notable target in AI-enabled cybersecurity risk.

Related Threat Clusters

  • Poetic Prompts Enable Jailbreaking of Large Language Models

    Researchers in Italy published a paper revealing that poetic prompts can effectively jailbreak large language models (LLMs). This technique, termed 'adversarial poetry,' demonstrated high attack-success rates across…

    2 articles · Updated November 28, 2025
  • Cisco Reports Vulnerabilities in Open-Weight LLMs to Multi-Turn Attacks

    Cisco's research reveals that popular open-weight large language models (LLMs) are highly vulnerable to multi-turn prompt injection attacks. These adaptive adversarial attacks can achieve success rates exceeding 90%…

    2 articles · Updated November 7, 2025

Recent Intelligence Reports

  • Rhyme is the key to set AIs free when verse outsmarts security — Theregister · November 21, 2025
  • Popular LLMs dangerously vulnerable to iterative attacks, says Cisco — Computerweekly · November 7, 2025

CVSS v3.1 Breakdown