2025
SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models.
CoRR, February, 2025

What's Done Is Not What's Claimed: Detecting and Interpreting Inconsistencies in App Behaviors.
Proceedings of the 32nd Annual Network and Distributed System Security Symposium, 2025

2024
CTRL: Clustering Training Losses for Label Error Detection.
IEEE Trans. Artif. Intell., August, 2024

Rule-based Data Selection for Large Language Models.
CoRR, 2024

Learning Interpretable Differentiable Logic Networks.
CoRR, 2024

Model-Enhanced LLM-Driven VUI Testing of VPA Apps.
CoRR, 2024

DARKFLEECE: Probing the Dark Side of Android Subscription Apps.
Proceedings of the 33rd USENIX Security Symposium, 2024

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-Supervised Learning.
Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

2023
A Data-free Backdoor Injection Approach in Neural Networks.
Proceedings of the 32nd USENIX Security Symposium, 2023

Invisible Backdoor Attacks Using Data Poisoning in Frequency Domain.
Proceedings of the ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland, 2023

2021
Bookworm Game: Automatic Discovery of LTE Vulnerabilities Through Documentation Analysis.
Proceedings of the 42nd IEEE Symposium on Security and Privacy, 2021