SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909030604079104 |
|---|---|
| author | Lin, Xixun Liu, Yang Chen, Yancheng Wu, Yongxuan Ning, Yucheng Liu, Yilong Sun, Nan Zhang, Shun Chong, Bin Zhou, Chuan Cao, Yanan |
| author_facet | Lin, Xixun Liu, Yang Chen, Yancheng Wu, Yongxuan Ning, Yucheng Liu, Yilong Sun, Nan Zhang, Shun Chong, Bin Zhou, Chuan Cao, Yanan |
| contents | The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the harness a high-value attack surface: a single compromise at the harness level can cascade through the entire execution pipeline. We observe that existing security approaches suffer from structural mismatch, leaving them blind to harness-internal state and unable to coordinate across the different phases of agent operation. In this paper, we introduce \safeharness{}, a security architecture in which four proposed defense layers are woven directly into the agent lifecycle to address above significant limitations: adversarial context filtering at input processing, tiered causal verification at decision making, privilege-separated tool control at action execution, and safe rollback with adaptive degradation at state update. The proposed cross-layer mechanisms tie these layers together, escalating verification rigor, triggering rollbacks, and tightening tool privileges whenever sustained anomalies are detected. We evaluate \safeharness{} on benchmark datasets across diverse harness configurations, comparing against four security baselines under five attack scenarios spanning six threat categories. Compared to the unprotected baseline, \safeharness{} achieves an average reduction of approximately 38\% in UBR and 42\% in ASR, substantially lowering both the unsafe behavior rate and the attack success rate while preserving core task utility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13630 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment Lin, Xixun Liu, Yang Chen, Yancheng Wu, Yongxuan Ning, Yucheng Liu, Yilong Sun, Nan Zhang, Shun Chong, Bin Zhou, Chuan Cao, Yanan Cryptography and Security Artificial Intelligence The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the harness a high-value attack surface: a single compromise at the harness level can cascade through the entire execution pipeline. We observe that existing security approaches suffer from structural mismatch, leaving them blind to harness-internal state and unable to coordinate across the different phases of agent operation. In this paper, we introduce \safeharness{}, a security architecture in which four proposed defense layers are woven directly into the agent lifecycle to address above significant limitations: adversarial context filtering at input processing, tiered causal verification at decision making, privilege-separated tool control at action execution, and safe rollback with adaptive degradation at state update. The proposed cross-layer mechanisms tie these layers together, escalating verification rigor, triggering rollbacks, and tightening tool privileges whenever sustained anomalies are detected. We evaluate \safeharness{} on benchmark datasets across diverse harness configurations, comparing against four security baselines under five attack scenarios spanning six threat categories. Compared to the unprotected baseline, \safeharness{} achieves an average reduction of approximately 38\% in UBR and 42\% in ASR, substantially lowering both the unsafe behavior rate and the attack success rate while preserving core task utility. |
| title | SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2604.13630 |