Lipeng He
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
arXiv 2025
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
arXiv 2025
Locket: Robust Feature-Locking Technique for Language Models
arXiv 2025
LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers