← Back to all news
arXiv Computation and Language By Zi Liang, Ronghua Li, Yanyun Wang, Qingqing Ye, Haibo Hu

Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure

Read the original on arXiv Computation and Language →

The paper introduces Mobius Injection, a new attack that turns autonomous LLM agents into zombie nodes capable of launching Agent-based and -Oriented DDoS (AbO-DDoS) attacks. By combining indirect prompt injection with persistent agent components through a mechanism called Semantic Closure, a single injection event can trigger sustained recursive execution of agent components. Experiments on three claw-style agents and three coding agents across 12 LLMs show that Mobius Injection can amplify single-node calls up to 51×, drain 123k–127k tokens per node on a shared five‑GPU backend, and increase benign request latency by 23–24×, eventually saturating shared capacity and denying service to legitimate traffic.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Jul 17

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

arXiv:2603. 15727v3 Announce Type: replace-cross Abstract: Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplored.

By Yihao Zhang, Zeming Wei, Xiaokun Luan, Chengcan Wu, Zhixin Zhang, Jiangrong Wu, Haolin Wu, Huanran Chen, Jun Sun, Meng Sun
llmsagents
More like this →
arXiv AI
Jul 31

SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response

arXiv:2607. 26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.

By Lehan Wang, Boli Chen, Ruixue Ding, Pengjun Xie, Jinwei Huang, Zhendong Liu, Shuo Wang, Tao Lei, Xin Ouyang, Xiaomeng Li
llmsagentsnlpbenchmarks
More like this →
arXiv AI
Oct 16

INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems

INFUSE is a new benchmark that tests indirect prompt injection (IPI) in large‑language‑model agents performing long‑horizon workflows. It contains 40 realistic tasks and 56 attack scenarios across five threat categories, with attacks injected through realistic interaction surfaces rather than just initial prompts. The study evaluated 19 LLMs, generating over 41,000 adversarial trajectories and found mean attack success rates of 19.6% (LLM evaluation) and 15.4% (heuristic verification), while prompt‑level hardening reduced success from 58.2% to 14.3%.

By Thuy Dung Nguyen, Jingyi Guo, Rana Seda Dubauskas, Sreepriya Damuluru, Taylor T. Johnson, Kevin Leach
llmsagentsmultimodalbenchmarkssafety
More like this →