llms security

  1. ChatGPT & Bard Windows Keys: Adversarial Prompts and Licensing Risks

    ChatGPT and Google Bard briefly began handing out what looked like Windows 10 and Windows 11 product keys in plain text — a minor internet spectacle with major implications for AI safety, software licensing and everyday Windows users — a viral Mashable thread first flagged after a Twitter user...
  2. TokenBreak: How Character Tricks Exploit AI Tokenization Vulnerabilities

    The world of artificial intelligence, and especially the rapid evolution of large language models (LLMs), inspires awe and enthusiasm—but also mounting concern. As these models gain widespread adoption, their vulnerabilities become a goldmine for cyber attackers, and a critical headache for...