Skip to content

Author

Xin-Jian Luo

We have 4 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security

Large language model based agents increasingly rely on external tools to invoke services and interact with web resources. These tools can evolve through software updates, yet agentic frameworks may continue trusting them without re-verifying their safety after implementation changes. This tool update gap creates a supp...

Shi-Yu Kan, Yue Qi, Yu-Fei Han et al. · 0 citations
Preprint Oct 2026

The Blind Spots of Detection: Adversarial Perturbation Attacks against Watchdogs in Distributed LLM Inference

Decentralizing large language model (LLM) inference across untrusted Web nodes requires robust verification to ensure computational integrity. Existing activation-based verification and detection mechanisms validate intermediate outputs against reference values, permitting bounded numerical deviations to accommodate be...

Siu-Wai Shi, Xiao-Chen Zhu, Xin-Jian Luo et al. · 0 citations
Book Open access Aug 2026

Black-Box Embedding Inversion Attack on Vector Databases

A novel black-box image embedding inversion attack that reconstructs high-fidelity images using only query access to the embedding model or API, and introduces an embedding-guided cross-attention mechanism, where image embeddings serve as conditional signals to steer the generation process.

Lichao Sun, Yun-Cheng Wu, Hai-Chao Sha et al. · 0 citations
Book Open access Aug 2026

Black-Box Embedding Inversion Attack on Vector Databases

A novel black-box image embedding inversion attack that reconstructs high-fidelity images using only query access to the embedding model or API, and introduces an embedding-guided cross-attention mechanism, where image embeddings serve as conditional signals to steer the generation process.

Lichao Sun, Yuncheng Wu, Haichao Sha et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.