Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916035970465792 |
|---|---|
| author | Ma, Jianan Du, Xiaohu Lin, Ruixiao Bian, Yaoxiang Chen, Jialuo Wang, Jingyi Yang, Xiaofang Cui, Shiwen Meng, Changhua Deng, Xinhao Wang, Zhen |
| author_facet | Ma, Jianan Du, Xiaohu Lin, Ruixiao Bian, Yaoxiang Chen, Jialuo Wang, Jingyi Yang, Xiaofang Cui, Shiwen Meng, Changhua Deng, Xinhao Wang, Zhen |
| contents | As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn, stateless behaviors, overlooking the expanded attack surface inherent in stateful, multi-turn interactions and dynamic tool invocations. In this paper, we propose a novel, multi-dimensional evasion framework targeting LLM-based agent systems. We introduce three stealthy attack vectors: (1) Temporal evasion, which fragments malicious payloads across sequential interaction turns; (2) Spatial evasion, which conceals payloads within complex external artifacts that evade standard LLM parsing mechanisms; and (3) Semantic evasion, which obscures malicious intents beneath benign contextual noise. To systematically quantify these threats, we construct A3S-Bench, a comprehensive benchmark comprising 2,254 real-world agent execution trajectories. Evaluating a standard agent framework separately integrated with 10 mainstream LLM backbones against 20 practical threat scenarios, we demonstrate that our evasion framework elevates the average risk trigger rate from a 28.3\% baseline to 52.6\%. These findings reveal systemic, architecture-level vulnerabilities in current autonomous agent systems that existing defenses fail to address, highlighting an urgent need for defense mechanisms tailored to the unique threats. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22321 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions Ma, Jianan Du, Xiaohu Lin, Ruixiao Bian, Yaoxiang Chen, Jialuo Wang, Jingyi Yang, Xiaofang Cui, Shiwen Meng, Changhua Deng, Xinhao Wang, Zhen Cryptography and Security Artificial Intelligence Software Engineering K.6.5, I.2.6 As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn, stateless behaviors, overlooking the expanded attack surface inherent in stateful, multi-turn interactions and dynamic tool invocations. In this paper, we propose a novel, multi-dimensional evasion framework targeting LLM-based agent systems. We introduce three stealthy attack vectors: (1) Temporal evasion, which fragments malicious payloads across sequential interaction turns; (2) Spatial evasion, which conceals payloads within complex external artifacts that evade standard LLM parsing mechanisms; and (3) Semantic evasion, which obscures malicious intents beneath benign contextual noise. To systematically quantify these threats, we construct A3S-Bench, a comprehensive benchmark comprising 2,254 real-world agent execution trajectories. Evaluating a standard agent framework separately integrated with 10 mainstream LLM backbones against 20 practical threat scenarios, we demonstrate that our evasion framework elevates the average risk trigger rate from a 28.3\% baseline to 52.6\%. These findings reveal systemic, architecture-level vulnerabilities in current autonomous agent systems that existing defenses fail to address, highlighting an urgent need for defense mechanisms tailored to the unique threats. |
| title | Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions |
| topic | Cryptography and Security Artificial Intelligence Software Engineering K.6.5, I.2.6 |
| url | https://arxiv.org/abs/2605.22321 |