English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the recent advent of Large Language Models (LLMs), such as ChatGPT fromOpenAI, BARD from Google, Llama2 from Meta, and Claude from Anthropic AI, gainwidespread use, ensuring their security and robustness is critical. Thewidespread use of these language models heavily relies on their reliability andproper usage of this fascinating technology. It is crucial to thoroughly testthese models to not only ensure its quality but also possible misuses of suchmodels by potential adversaries for illegal activities such as hacking. Thispaper presents a novel study focusing on exploitation of such large languagemodels against deceptive interactions. More specifically, the paper leverageswidespread and borrows well-known techniques in deception theory to investigatewhether these models are susceptible to deceitful interactions.  This research aims not only to highlight these risks but also to pave the wayfor robust countermeasures that enhance the security and integrity of languagemodels in the face of sophisticated social engineering tactics. Throughsystematic experiments and analysis, we assess their performance in thesecritical security domains. Our results demonstrate a significant finding inthat these large language models are susceptible to deception and socialengineering attacks.

Exploiting Large Language Models (LLMs) through Deception Techniques and Persuasion Principles