Russia is putting generative artificial intelligence to work in online deception campaigns, but its efforts have been unsuccessful, according to a Meta security report released on Thursday. The parent company of Facebook and Instagram found that so far AI-powered tactics "provide only incremental productivity and content-generation gains" for bad actors and Meta has been able to disrupt deceptive influence operations. Meta's efforts to combat "coordinated inauthentic behavior" on its platforms come as fears mount that generative AI will be used to trick or confuse people in elections in the United States and other countries. Russia remains the top source of "coordinated inauthentic behavior" using bogus Facebook and Instagram accounts, David Agranovich, Meta's security policy director, told reporters. Since Russia's invasion of Ukraine in 2022, those efforts have been concentrated on undermining Ukraine and its allies, according to the report.

The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models, deliberately designed to align with ethical standards and human values. Contrary to the prevalent assumption that the inherent instruction-following limitations of base LLMs serve as a safeguard against misuse, our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions. To systematically assess these risks, we introduce a novel set of risk evaluation metrics. Empirical results reveal that the outputs from base LLMs can exhibit risk levels on par with those of models fine-tuned for malicious purposes. This vulnerability, requiring neither specialized knowledge nor training, can be manipulated by almost anyone, highlighting the substantial risk and the critical need for immediate attention to the base LLMs' security protocols.