The paper surveys security risks of LLM agents, organizes them into a five-level autonomy taxonomy, and proposes an untested CMDP-based architecture called R2A2.
Further study on forbidden subgraphs of power graph
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
The undirected power graph (or simply power graph) of a group $G$, denoted by $P(G)$, is a graph whose vertices are the elements of the group $G$, in which two vertices $u$ and $v$ are adjacent if and only if either $u=v^m$ or $v=u^n$ for some positive integers $m$, $n$. Forbidden subgraph has a significant role in graph theory. In our previous work \cite{cmm}, we consider five important classes of forbidden subgraphs of power graph which include perfect graphs, cographs, chordal graphs, split graphs and threshold graphs. In this communication, we go even further in that way. This study, inspired by the articles \cite{celmmp,dong,ck}, examines additional $4$ significant forbidden classes, including chain graphs, diamond-free graphs, $\{P_{5}, \overline{P_{5}}\}$-free graphs and $\{P_{2}\cup P_{3}, \overline{P_{2}\cup P_{3}}\}$-free graph. The finite groups whose power graphs are chain graphs, diamond-free graphs, and $\{P_{2}\cup P_{3}, \overline{P_{2}\cup P_{3}}\}$-free graphs have been successfully identified in this work. In case of $\{P_{5}, \overline{P_{5}}\}$-free graphs, we completely determine all the nilpotent groups, direct product of two groups, finite simple groups whose power graph is $\{P_{5}, \overline{P_{5}}\}$-free.
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
The paper surveys security risks of LLM agents, organizes them into a five-level autonomy taxonomy, and proposes an untested CMDP-based architecture called R2A2.