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

Xiaojun Jia

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×3Vision×1AI×1

Frequent co-authors

Tingda Shen1×
Yebo Feng1×
Konglin Zhu1×
Yang Liu1×
Lin Zhang1×
Weiwei Qi1×

Research Timeline

2026
CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

The paper proposes CAAP, a capture-aware adversarial patch framework, demonstrating that deep palmprint recognition systems remain vulnerable to physically realizable attacks despite existing defenses.

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models

The paper proposes the Expected Safety Impact (ESI) framework to identify safety-critical parameters in LLMs, introducing targeted tuning methods (SET and SPA) to enhance safety and preserve alignment during model adaptation.

Sealing the Audit-Runtime Gap for LLM Skills

The paper introduces SIGIL, a novel framework that cryptographically seals the entire lifecycle of LLM skills, ensuring verifiable integrity from publication through runtime execution to prevent supply chain attacks.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 6, 2026

Sealing the Audit-Runtime Gap for LLM Skills

Tingda Shen, Yebo Feng, Konglin Zhu, Xiaojun Jia +2 more

The paper introduces SIGIL, a novel framework that cryptographically seals the entire lifecycle of LLM skills, ensuring verifiable integrity from publication through runtime execution to prevent suppl…

View →
cs.CRRecentApr 9, 2026

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models

Weiwei Qi, Zefeng Wu, Tianhang Zheng, Zikang Zhang +3 more

The paper proposes the Expected Safety Impact (ESI) framework to identify safety-critical parameters in LLMs, introducing targeted tuning methods (SET and SPA) to enhance safety and preserve alignment…

View →
cs.CVcs.AIcs.CRRecentApr 8, 2026

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

Renyang Liu, Jiale Li, Jie Zhang, Cong Wu +5 more

The paper proposes CAAP, a capture-aware adversarial patch framework, demonstrating that deep palmprint recognition systems remain vulnerable to physically realizable attacks despite existing defenses…

View →