Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380353722> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4380353722 abstract "Large Language Models (LLMs), renowned for their superior proficiency in language comprehension and generation, stimulate a vibrant ecosystem of applications around them. However, their extensive assimilation into various services introduces significant security risks. This study deconstructs the complexities and implications of prompt injection attacks on actual LLM-integrated applications. Initially, we conduct an exploratory analysis on ten commercial applications, highlighting the constraints of current attack strategies in practice. Prompted by these limitations, we subsequently formulate HouYi, a novel black-box prompt injection attack technique, which draws inspiration from traditional web injection attacks. HouYi is compartmentalized into three crucial elements: a seamlessly-incorporated pre-constructed prompt, an injection prompt inducing context partition, and a malicious payload designed to fulfill the attack objectives. Leveraging HouYi, we unveil previously unknown and severe attack outcomes, such as unrestricted arbitrary LLM usage and uncomplicated application prompt theft. We deploy HouYi on 36 actual LLM-integrated applications and discern 31 applications susceptible to prompt injection. 10 vendors have validated our discoveries, including Notion, which has the potential to impact millions of users. Our investigation illuminates both the possible risks of prompt injection attacks and the possible tactics for mitigation." @default.
- W4380353722 created "2023-06-13" @default.
- W4380353722 creator A5000432413 @default.
- W4380353722 creator A5008659449 @default.
- W4380353722 creator A5016856595 @default.
- W4380353722 creator A5023363049 @default.
- W4380353722 creator A5028270700 @default.
- W4380353722 creator A5029243457 @default.
- W4380353722 creator A5067390667 @default.
- W4380353722 creator A5068561556 @default.
- W4380353722 creator A5084868951 @default.
- W4380353722 date "2023-06-08" @default.
- W4380353722 modified "2023-10-18" @default.
- W4380353722 title "Prompt Injection attack against LLM-integrated Applications" @default.
- W4380353722 doi "https://doi.org/10.48550/arxiv.2306.05499" @default.
- W4380353722 hasPublicationYear "2023" @default.
- W4380353722 type Work @default.
- W4380353722 citedByCount "0" @default.
- W4380353722 crossrefType "posted-content" @default.
- W4380353722 hasAuthorship W4380353722A5000432413 @default.
- W4380353722 hasAuthorship W4380353722A5008659449 @default.
- W4380353722 hasAuthorship W4380353722A5016856595 @default.
- W4380353722 hasAuthorship W4380353722A5023363049 @default.
- W4380353722 hasAuthorship W4380353722A5028270700 @default.
- W4380353722 hasAuthorship W4380353722A5029243457 @default.
- W4380353722 hasAuthorship W4380353722A5067390667 @default.
- W4380353722 hasAuthorship W4380353722A5068561556 @default.
- W4380353722 hasAuthorship W4380353722A5084868951 @default.
- W4380353722 hasBestOaLocation W43803537221 @default.
- W4380353722 hasConcept C112930515 @default.
- W4380353722 hasConcept C134066672 @default.
- W4380353722 hasConcept C144133560 @default.
- W4380353722 hasConcept C151730666 @default.
- W4380353722 hasConcept C158379750 @default.
- W4380353722 hasConcept C199360897 @default.
- W4380353722 hasConcept C2779343474 @default.
- W4380353722 hasConcept C38652104 @default.
- W4380353722 hasConcept C41008148 @default.
- W4380353722 hasConcept C511192102 @default.
- W4380353722 hasConcept C86803240 @default.
- W4380353722 hasConceptScore W4380353722C112930515 @default.
- W4380353722 hasConceptScore W4380353722C134066672 @default.
- W4380353722 hasConceptScore W4380353722C144133560 @default.
- W4380353722 hasConceptScore W4380353722C151730666 @default.
- W4380353722 hasConceptScore W4380353722C158379750 @default.
- W4380353722 hasConceptScore W4380353722C199360897 @default.
- W4380353722 hasConceptScore W4380353722C2779343474 @default.
- W4380353722 hasConceptScore W4380353722C38652104 @default.
- W4380353722 hasConceptScore W4380353722C41008148 @default.
- W4380353722 hasConceptScore W4380353722C511192102 @default.
- W4380353722 hasConceptScore W4380353722C86803240 @default.
- W4380353722 hasLocation W43803537221 @default.
- W4380353722 hasOpenAccess W4380353722 @default.
- W4380353722 hasPrimaryLocation W43803537221 @default.
- W4380353722 hasRelatedWork W2051458263 @default.
- W4380353722 hasRelatedWork W2110890874 @default.
- W4380353722 hasRelatedWork W2123495254 @default.
- W4380353722 hasRelatedWork W2370877204 @default.
- W4380353722 hasRelatedWork W2382790131 @default.
- W4380353722 hasRelatedWork W2388380089 @default.
- W4380353722 hasRelatedWork W2393107288 @default.
- W4380353722 hasRelatedWork W2764151937 @default.
- W4380353722 hasRelatedWork W2937491416 @default.
- W4380353722 hasRelatedWork W3097079723 @default.
- W4380353722 isParatext "false" @default.
- W4380353722 isRetracted "false" @default.
- W4380353722 workType "article" @default.