The underground exploitation of large language models (LLMs) for malicious services (i.e., Malla) is witnessing an uptick, amplifying the cyber threat landscape and posing questions about the trustworthiness of LLM technologies. However, there has been little effort to understand this new cybercrime, in terms of its magnitude, impact, and techniques. In this paper, we conduct the first systematic study on 212 real-world Mallas, uncovering their proliferation in underground marketplaces and exposing their operational modalities. Our study discloses the Malla ecosystem, revealing its significant growth and impact on today's public LLM services. Through examining 212 Mallas, we uncovered eight backend LLMs used by Mallas, along with 182 prompts that circumvent the protective measures of public LLM APIs. We further demystify the tactics employed by Mallas, including the abuse of uncensored LLMs and the exploitation of public LLM APIs through jailbreak prompts. Our findings enable a better understanding of the real-world exploitation of LLMs by cybercriminals, offering insights into strategies to counteract this cybercrime.

Public Wiki systems are collaborative knowledge bases More specifically, a research question is that, given a query, that anyone can contribute. This open model is user-friendly whether strategic revisions can be made on selected Wiki and powerful, which reduces participation barriers and allows articles (which we call adversarial revisions) to ensure people with different backgrounds to contribute. As that the following goals are achieved simultaneously: 1) a prominent example of public Wiki systems, Wikipedia the ranks of the revised articles are significantly improved is instrumental in making open knowledge that millions of among query results, 2) the revisions cannot be detected people use, redistribute, and contribute to [28]. In another by Wiki vandalism detection even when the detector is instance, Wikidata [83] is a free and open knowledge base blackbox to the adversary, and 3) the content of revisions with 0.1 billion data items that can be read and edited does not arouse any suspicion from Wiki users but can still by both humans and machines. Public Wiki systems have capture their attention by keeping the semantic consistency already served as key knowledge sources in people's daily and topic relevancy of the revised articles.