3 papers
cs.LG2026
Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates
Weiyi He, Yuping Lin, Jiliang Tang +1
Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large langua…
stat.ML2026
Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression
Weiyi He, Yue Xing
Positional encoding (PE) is a core architectural component of Transformers, yet its impact on the Transformer's generalization and robustness remains unclear. In this work, we prov…
cs.CR2025
Unveiling Privacy Risks in LLM Agent Memory
Bo Wang, Weiyi He, Shenglai Zeng +4
Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions…