Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/JianFeng Ma

JianFeng Ma

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×5ML×1Vision×1AI×1

Frequent co-authors

Yulong Shen4×
Di Lu3×
Xuewen Dong3×
Zhiquan Liu2×
Yongzhi Liao2×
Yuchen Zhang1×

Research Timeline

2026
When Convenience Becomes Risk: A Semantic View of Under-Specification in Host-Acting Agents

The paper identifies that the convenience of host-acting agents leads to semantic under-specification in user goals, which forces the agent to generate potentially risky execution plans.

Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation

The paper proposes an operation-centric, TEE-backed isolation model to constrain self-hosted computer-use agents, preventing malicious or unsafe host-level operations without sacrificing general functionality.

EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration

The paper introduces EBCC, an OCI-compatible runtime architecture that manages composite confidential-computing workloads by integrating TEE-backed execution into the standard container lifecycle.

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Models (LVLMs).

IstGPT: LLM-based Anomaly Detection for Spatial-Temporal Graph in Industrial Systems

IstGPT introduces a novel LLM-based framework for real-time, fine-grained anomaly detection in complex industrial cyber-physical systems, achieving state-of-the-art performance across multiple benchmarks.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGRecentJun 1, 2026

IstGPT: LLM-based Anomaly Detection for Spatial-Temporal Graph in Industrial Systems

Yuchen Zhang, Ning Xi, Pengbin Feng, Shigang Liu +4 more

IstGPT introduces a novel LLM-based framework for real-time, fine-grained anomaly detection in complex industrial cyber-physical systems, achieving state-of-the-art performance across multiple benchma…

View →
cs.CRcs.CVRecentMay 15, 2026

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation

Hao Yang, Zhuo Ma, Yang Liu, Yilong Yang +2 more

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…

View →
cs.CRRecentMay 13, 2026

EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration

Di Lu, Qingwen Zhang, Yujia Liu, Xuewen Dong +3 more

The paper introduces EBCC, an OCI-compatible runtime architecture that manages composite confidential-computing workloads by integrating TEE-backed execution into the standard container lifecycle.

View →
cs.CRRecentMay 7, 2026

Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation

Di Lu, Bo Zhang, Xiyuan Li, Yongzhi Liao +4 more

The paper proposes an operation-centric, TEE-backed isolation model to constrain self-hosted computer-use agents, preventing malicious or unsafe host-level operations without sacrificing general funct…

View →
cs.CRcs.AIRecentMar 22, 2026

When Convenience Becomes Risk: A Semantic View of Under-Specification in Host-Acting Agents

Di Lu, Yongzhi Liao, Xutong Mu, Lele Zheng +4 more

The paper identifies that the convenience of host-acting agents leads to semantic under-specification in user goals, which forces the agent to generate potentially risky execution plans.

View →