Topic: frontier ai

Sort by: Relevance | Date
  • UK NCSC Backs Public Disclosure of AI Security Flaws
    September 3, 2025
    75%

    UK NCSC Backs Public Disclosure of AI Security Flaws

    UK cybersecurity and AI authorities advocate for crowdsourced initiatives to identify and address AI vulnerabilities, emphasizing the rising risks from malicious exploitation of advanced platforms. In response to AI system breaches, developers have launched bug bounty programs to incentivize ethi...

    Read More »
  • AI Researchers Withhold 'Dangerous' AI Incantations
    December 9, 2025
    60%

    AI Researchers Withhold 'Dangerous' AI Incantations

    Researchers discovered that crafting harmful prompts into poetry can bypass the safety guardrails of major AI systems, exposing a critical weakness in their alignment. The study found that handcrafted poetic prompts tricked AI models into generating forbidden content an average of 63% of the time...

    Read More »

Related Topics

large language models (1) ai safety (1) ransomware threats (1) ai guardrails (1) cybercriminal activities (1) ai misuse (1) industry collaboration (1) research study (1)