November 19, 2026 USD 45.20EUR 49.57PLN 11.24
Новини Глухів — коротко й по суті
LIVE
Kremlin Statements on the War: New Rhetoric Regarding Conflict Resolution Assessment of Drone Production in Russia for 2027: Expert Comments on Industrial Capabilities Pensioner and 600 Pigeons Evacuated from Frontline Kramatorsk Invaders announce launch of boats across Kerch Strait after strikes on bridge UN International Court of Justice finds Myanmar responsible for genocide Energy independence during winter blackouts: Are solar panels worth installing Putin Threatens Ukraine with Harsh Response Over Crimean Bridge Strikes China Restricts Drone Component Exports: Ukraine Explains Why It Is Not Enough Neptune Missile Strike Damages Railway Track on Crimean Bridge Border guards destroy nearly sixty enemy drones in Sumy region Kremlin Statements on the War: New Rhetoric Regarding Conflict Resolution Assessment of Drone Production in Russia for 2027: Expert Comments on Industrial Capabilities Pensioner and 600 Pigeons Evacuated from Frontline Kramatorsk Invaders announce launch of boats across Kerch Strait after strikes on bridge UN International Court of Justice finds Myanmar responsible for genocide Energy independence during winter blackouts: Are solar panels worth installing Putin Threatens Ukraine with Harsh Response Over Crimean Bridge Strikes China Restricts Drone Component Exports: Ukraine Explains Why It Is Not Enough Neptune Missile Strike Damages Railway Track on Crimean Bridge Border guards destroy nearly sixty enemy drones in Sumy region

AI Vulnerability: How Manipulations Cause Algorithms to Target Civilian Objects

💡 Tech 1 min read 👁 0

Research by Vals analysts shows that popular AI models can bypass ethical safeguards if their actions are framed as a game.

AI Vulnerability: How Manipulations Cause Algorithms to Target Civilian Objects💡Tech

Photo: RBC-Ukraine

Key points

  • AI models mistakenly identify civilian objects as military targets
  • Safety filters are easily bypassed through context manipulation
  • Developers are preparing additional safety measures to prevent misuse

Modern artificial intelligence models developed by leading global companies have demonstrated a dangerous propensity for errors when analyzing autonomous warfare scenarios. According to a report by Vals analysts, even complex systems like Claude Opus 5.5 are capable of identifying civilian objects as military targets if the user manipulates the query context.

Bypassing Safety Protocols

Researchers discovered that built-in safety filters are easily circumvented by simply labeling a simulation as a "game." During experiments based on real imagery from Ukraine and Iran, AI models regularly flagged schools and surrendering soldiers for attack. Specifically, the Claude Opus 5.5 model selected an Iranian school as a target in 72% of cases when the task was presented as a game.

Representatives from developers, including Anthropic and OpenAI, have acknowledged these results as unacceptable. They have announced plans to strengthen safety barriers and block attempts to use AI in conjunction with drone systems. Currently, technical limitations, such as a lack of onboard computing power for drones, hinder the mass deployment of such solutions, but experts warn against using AI to analyze combat footage.

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.