Zhou Li

Making Tagging Systems Resistant to Tricky Spam Attacks

2015

Tagging systems are known vulnerable to tag spam. While there have been efforts aiming at addressing this problem, tricky spam attackers could exploit and leverage vulnerabilities within them to invalidate these seemingly robust efforts. Rather …

Your Smart Home Can't Keep a Secret: Towards Automated Fingerprinting of IoT Traffic with Neural Networks

2019 · arXiv (Cornell University)

The IoT (Internet of Things) technology has been widely adopted in recent years and has profoundly changed the people's daily lives. However, in the meantime, such a fast-growing technology has also introduced new privacy issues, …

Automatic Generation of Adversarial Readable Chinese Texts

2022 · IEEE Transactions on Dependable and Secure Computing

Natural language processing (NLP) models are known vulnerable to adversarial examples, similar to image processing models. Studying adversarial texts is an essential step to improve the robustness of NLP models. However, existing studies mainly focus …

Investigation and application of key technologies of aggregated flash payment based on marketing blockchain in the context of massive distributed generation grid connection

2023 · International Journal of Emerging Electric Power Systems

Abstract Optical flash payment technology is a form of optical flash payment application. Its payment scenario is mainly to directly realize “card free payment” in the consumption process through mobile devices, Bluetooth and other connection …

Utilizing Contextual Clues and Role Correlations for Enhancing Document-Level Event Argument Extraction

2025 · IEEE Transactions on Audio Speech and Language Processing

Document-level event argument extraction is a crucial yet challenging task within the field of information extraction. Current mainstream approaches primarily focus on the information interaction between event triggers and their arguments, facing two limitations: insufficient …

Dynamic Risk Assessments for Offensive Cybersecurity Agents

2025

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents, but most fail to account …