Author

Xiao-Jun Jia

h-index 4 View on Semantic Scholar

We have 3 of 13 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 Oct 2026

ASCENT: First-Order Optimal Fine-Tuning with Recalibration for Safety--Utility Co-Enhancement

Supervised fine-tuning can substantially improve the downstream utility of large language models (LLMs) but may compromise their safety. Existing safety-preserving methods constrain downstream updates using safety-related parameters or subspaces, but mainly focus on safety preservation rather than joint safety and util...

Wei-Wei Qi, Chong-Yu Wang, Tian-Hang Zheng et al. · 0 citations

Preprint Aug 2026

ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization

Agent skills, bundles of instructions and resources that an LLM agent loads on demand, form an emerging supply chain where a single poisoned skill can persistently compromise every agent that installs it. However, existing skill attacks either fire on every request or rely on fine-tuned weights or multiple skills, leav...

Hao Sui, Simeng Qin, Jie Liao et al. · 0 citations

Preprint Aug 2026

ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners

ColluSkill is proposed, a collusive multi-skill-chain attack framework that decomposes a complete malicious intent into interdependent sub-payloads embedded in independently packaged skills and employs LLM-based chain planning and scanner-feedback refinement to preserve chain-level attack semantics.

Pu-Yu Zeng, Simeng Qin, Jingzhi Li et al. · 1 citation