Get the latest tech news
Gemini hackers can deliver more potent attacks with a helping hand from… Gemini
Hacking LLMs has always been more art than science. A new attack on Gemini could change that.
In the growing canon of AI security, the indirect prompt injection has emerged as the most powerful means for attackers to hack large language models such as OpenAI’s GPT-3 and GPT-4 or Microsoft’s Copilot. Despite the power of prompt injections, attackers face a fundamental challenge in using them: The inner workings of so-called closed-weights models such as GPT, Anthropic’s Claude, and Google’s Gemini are closely held secrets. The resulting insights revealed that "the training loss serves as an almost perfect proxy for the adversarial objective function when the length of the target string is long," Nishit Pandya, a co-author and PhD student at UC San Diego, concluded.
Or read this on ArsTechnica
