2 papers
cs.CL2025
Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks
Narek Maloyan, Bislan Ashinov, Dmitry Namiot
Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text. This paradigm offers scalability and cost…
cs.CL2024
Trojan Detection in Large Language Models: Insights from The Trojan Detection Challenge
Narek Maloyan, Ekansh Verma, Bulat Nutfullin +1
Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, but their vulnerability to trojan or backdoor attacks poses significant security risks. T…