November 20, 2026 USD 45.05EUR 49.53PLN 11.22
Новини Ковель — коротко й по суті
LIVE
International Partners Announce Legally Binding Security Guarantees for Ukraine Ukraine to Receive Large-Scale Support from EU and NATO: Details of Berlin Agreements The road sign with a crossed-out finger: what it actually means Name Day on November 27: Who Celebrates November 20: World Pediatrician Day and its importance for Kovel Oleksandr Usyk shares details of his interactions with global sports stars Defense Forces neutralize Russian drone operators in Kherson region Fuel market in Ukraine: prices for gasoline and diesel show a sharp decline German Chancellor Friedrich Merz suggests UAE as a potential venue for four-party talks on ending the war Volodymyr Zelenskyy questions the interpretation of NATO-style security guarantees International Partners Announce Legally Binding Security Guarantees for Ukraine Ukraine to Receive Large-Scale Support from EU and NATO: Details of Berlin Agreements The road sign with a crossed-out finger: what it actually means Name Day on November 27: Who Celebrates November 20: World Pediatrician Day and its importance for Kovel Oleksandr Usyk shares details of his interactions with global sports stars Defense Forces neutralize Russian drone operators in Kherson region Fuel market in Ukraine: prices for gasoline and diesel show a sharp decline German Chancellor Friedrich Merz suggests UAE as a potential venue for four-party talks on ending the war Volodymyr Zelenskyy questions the interpretation of NATO-style security guarantees

Research reveals AI vulnerability to manipulation in military scenarios

💡 Tech 1 min read 👁 0

Analysts have discovered that modern AI models can flag civilian objects as military targets if the request is framed as a game.

Research reveals AI vulnerability to manipulation in military scenarios💡Tech

Photo: RBC-Ukraine

Key points

  • AI models bypass filters via game scenarios
  • Civilian objects are wrongly identified as targets
  • Developers are creating additional safety mechanisms

New research from Vals has demonstrated critical security gaps in systems developed by leading AI companies, including OpenAI, Google, and Anthropic. Experiments revealed that AI models can identify civilian objects and people as potential targets if a user manipulates the context settings.

Security bypass mechanisms

Researchers utilized real satellite and drone imagery covering parts of Ukraine and Iran. It was found that even simple framing of a task as a "game" allows the bypassing of internal safety filters. Specifically, the Claude Opus 5.5 model classified a civilian school near a military complex as a target in 72% of cases when the scenario was presented as a game.

Representatives from Anthropic and OpenAI acknowledged the audit results as concerning and stated they are working on strengthening safety barriers to prevent the use of AI in military applications.

While technical constraints, such as latency and limited onboard computing power for drones, currently hinder the integration of AI directly into weapons, experts warn of the risks of using these technologies for automated analysis of combat footage and training target acquisition systems.

Source RBC-Ukraine — rbc.ua/ukr/news/dostatno-nazvati-boyovi-diyi-groyu-claude-179501202… ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.