Tag

#DeepSeek

8 stories taggedDeepSeek.

A threat intelligence dashboard displaying data flow arrows pointing from multiple locations to major AI model diagrams, with geographic markers and attribution
AI Security

US Agencies Say Chinese AI Firms Are Stealing From American Models at Industrial Scale

A joint NSA, CISA and FBI advisory names DeepSeek, Alibaba, Moonshot AI, MiniMax, StepFun and Z.AI as running organised campaigns to copy the inner workings of Claude, GPT, Gemini and Grok.

4 min read
A developer's dual-monitor setup with a code editor showing an AI agent sandbox environment, and the agent visibly breaking through the illustrated containment
AI Security

DeepSeek's Coding Agent Could Switch Off Its Own Safety Cage

A flaw in DeepSeek Harness let an AI agent escape the sandbox meant to keep it away from the rest of a developer's computer.

3 min read
A computer screen displaying lines of code and network diagrams in the dark, with cascading error messages and system alerts visible, suggesting automated intru
Threat Intelligence

AI Agents Ran a Four-Day Hacking Campaign Against Taiwan's Government Systems

Researchers say a cluster of AI programs worked in near-total automation to steal credentials, map government networks, and probe a nuclear safety agency, a sign that organised hacking is getting cheaper and faster.

4 min read
A smartphone screen displaying a Telegram chat interface with an AI agent executing commands autonomously, system notifications showing target selection and exp
AI Security

Chinese Operator Turns DeepSeek Into a Self-Driving Hacker via Telegram

Unit 42 says an attacker gave one Telegram command and let an AI agent pick the targets, choose the exploits, and run the intrusion on its own.

3 min read
A split-screen visualization showing attack and defense timelines accelerating simultaneously, with automation nodes and AI decision points multiplying on both
AI Security

AI Is Compressing the Cybersecurity Timeline. Security Teams Are Racing to Keep Up.

Artificial intelligence is speeding up both attack and defence at the same time. The organisations that survive the shift may not be the best-defended. They may simply be the fastest to act.

3 min read
Illustration: a laptop screen displaying an abstract browser window with a ghostly file-picker dialog overlay
AI Security

DeepSeek-Generated PoC Ransomware Runs Entirely in the Browser via Chromium File System Access API

Researchers documented what they describe as the first frontier-model-produced malware artifact that fuses LLM ideation with a legitimate Chromium capability to encrypt user files without dropping a single native binary.

3 min read
Illustration: a generic laptop screen glowing in a dim room
AI Security

DeepSeek Spits Out Working Browser-Native Ransomware for Windows and Android

Researchers say a frontier model stitched together a real Chromium capability with discarded malware concepts and produced something that actually encrypts files from inside a tab.

3 min read
Illustration: a developer workstation at dusk, glowing IDE on a dark monitor with abstract plugin tiles floating above
AI Security

Fifteen Rogue JetBrains Plugins Posed as DeepSeek Assistants to Siphon AI Keys

A coordinated campaign on the JetBrains Marketplace dressed up credential stealers as LLM-powered coding helpers. The payload: your provider keys.

3 min read
© 2026 Threat Vectr