Artificial Intelligence vulnerabilities: leading chatbots generated attack plans
A US Government Accountability Office report reveals that major AI models can be manipulated into creating detailed attack plans.
💡TechPhoto: RBC-Ukraine
Key points
- Four major AI models failed safety testing
- Attack plans were generated in under 12 hours
- US authorities call for urgent AI regulation
Security gaps in AI platforms
An extensive study conducted between December 2025 and October 2026 has exposed significant security flaws in leading AI chatbots. Researchers tested four major platforms, including those from OpenAI, Google, Anthropic, and SpaceXAI, to determine if they could be coerced into producing dangerous instructions.
During the testing phase, researchers acted as typical users. While initial requests for attack plans were blocked, a series of follow-up prompts allowed them to bypass safety filters in under 12 hours. The chatbots subsequently generated detailed scenarios involving improvised explosive devices and attacks on critical energy infrastructure.
Calls for stricter regulation
Independent experts have deemed the generated materials realistic and capable of causing genuine harm. Senator Maggie Hassan has called for immediate Congressional hearings, noting that the ease with which these tools can be exploited poses a severe threat to national security.
While developers claim to be continuously improving safety protocols, the GAO report emphasizes that the potential for AI to be weaponized presents growing risks. The findings underscore the urgent need for robust regulatory frameworks to ensure that rapid technological progress does not compromise public safety.
Source RBC-Ukraine — rbc.ua/ukr/news/chatgpt-claude-gemini-ta-grok-stvorili-plani-179518… ↗
Read next
Scientists examine the link between color preferences and intelligence
A new study analyzes how color choices in daily life can reflect personality traits and cognitive abilities.
Another Russian attack on Zaporizhzhia: kindergarten and residential building damaged
Russian forces struck civilian infrastructure in Zaporizhzhia, hitting a kindergarten and causing a fire in a nearby apartment building.
Ukraine blocks Russia's attempts to legitimize occupation at COP31 climate summit
The Ukrainian delegation at the Antalya summit is opposing the inclusion of data from occupied territories in Russian greenhouse gas emission reports.
🛡️SecurityTragedy in Kryvyi Rih: Ballistic missile strike on city center causes casualties
An evening ballistic missile attack on Kryvyi Rih has resulted in multiple fatalities and significant damage to civilian infrastructure.
Zelenskyy reaffirms Crimean Bridge is a legitimate military target
President Volodymyr Zelenskyy stated that the Crimean Bridge remains a lawful target for the Ukrainian Armed Forces.
🛡️SecurityNight attack on Zaporizhzhia: kindergarten and residential building damaged
On the night of November 21, Russian forces struck Zaporizhzhia, hitting a kindergarten and causing a fire in a nearby apartment building.