Lattice AI Research

Research focus

Red-Teaming & Adversarial Robustness (2)Recommendation & Information Retrieval (1)Open-Source Models & Weights (1)

Frequent co-authors

Bolin Shen (2)Yushun Dong (2)Md Shamim Seraj (1)Shayok Chakraborty (1)

Papers (2)

Feb 23, 2026

2w ago

CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense

Stop model extraction attacks on your GNNs without sacrificing accuracy: CITED uses a novel decision boundary signature to prove ownership at both the embedding and label levels.

Bolin Shen, Md Shamim Seraj, Zhan Cheng +2

Recommendation & Information Retrieval Red-Teaming & Adversarial Robustness

2w ago·also Florida State

CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks

Finally, a defense against model extraction comes with rigorous theoretical guarantees, using mutual information to certify DNN ownership.

Bolin Shen, Zhan Cheng, Neil Zhenqiang Gong +2

Open-Source Models & Weights Red-Teaming & Adversarial Robustness

Search

Zhan Cheng

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)