paperMay 2026UnreviewedOpen access

Securing LLM-based agents against cyberattacks: a comprehensive survey on attack techniques and defense strategies

Nyashadzashe Tamuka, T. Mathonsi, T. Olwal, Solly Maswikaneng, Tonderai Muchenje, T. Tshilongamulenzhe

Journal of Computer Virology and Hacking Techniques

Abstract

Large Language Model (LLM)-based agents integrate various models, including planning loops, memory, tool use, and multi-agent systems, enabling autonomous decision-making through natural-language interfaces. This autonomy also expands the cyberattack surface from model-only failures to agent compromise, where untrusted text can exfiltrate data or trigger malicious actions. This survey presents a taxonomy-driven synthesis of security threats targeting LLM-based agents and a structured review of

Framework mappings

OWASP Top 10 for Agentic Applications

ASI02Tool Misuse & Exploitation

MITRE ATLAS

AML.T0053AI Agent Tool Invocation

Suggested from the entry's categories.

Cite

@article{tamuka2026securing,
  title = {{Securing LLM-based agents against cyberattacks: a comprehensive survey on attack techniques and defense strategies}},
  author = {Nyashadzashe Tamuka and T. Mathonsi and T. Olwal and Solly Maswikaneng and Tonderai Muchenje and T. Tshilongamulenzhe},
  year = {2026},
  month = may,
  journal = {Journal of Computer Virology and Hacking Techniques},
  doi = {10.1007/s11416-026-00622-3},
  url = {https://www.semanticscholar.org/paper/604332431f17ceaefa260471b1792ce48ea7ff16}
}