Xiaodong Li
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2AI×1ML×1
Frequent co-authors
Research Timeline
2026
Mask-Free Privacy Extraction and Rewriting: A Domain-Aware Approach via Prototype Learning
The paper proposes DAMPER, a domain-aware framework that autonomously extracts and rewrites private information from text while providing rigorous differential privacy guarantees, significantly improving the privacy-utility trade-off.
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
The paper introduces a framework using the 'behavioral geometry' of model populations to efficiently predict jailbreak susceptibility and transfer defenses, achieving high accuracy with significantly fewer evaluations.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.LGRecentMay 26, 2026
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
The paper introduces a framework using the 'behavioral geometry' of model populations to efficiently predict jailbreak susceptibility and transfer defenses, achieving high accuracy with significantly…
View →
cs.CRRecentApr 11, 2026