Xiaojun Jia
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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.
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.
Papers
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…