Author

Zifeng Kang

Observed name: Kang, Zifeng

Institutions: Beijing University of Posts and Telecommunications, Shanghai Key Laboratory of Trustworthy Computing

Observed institutions: Beijing University of Posts and Telecommunications, Shanghai Key Laboratory of Trustworthy Computing

OpenAlex ID: A5129918646

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning

2026 · Zhenhao Zhu, Yue Liu, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2

Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications

2026 · Luo, Yang, Ji, Tiantian, et al. · arXiv (Cornell University)

A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors

2026 · Li, Pengxun, Zhang, Litian, et al. · arXiv (Cornell University)

VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers

2026 · Sun, Pengyu, Kang, Zifeng, et al. · arXiv (Cornell University)

Practical Covert Channel Across Isolated Browser Instances via GPU Command Queue Contention

2026 · Jinhong Liu, Zifeng Kang, et al. · IEEE Symposium on Security and Privacy (S&P)

ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts

2026 · Luo, Yang, Kang, Zifeng, et al. · arXiv (Cornell University)

Marking the Margin: Robust DNN Watermarking Against Removal Attacks via Sculpting Decision Boundaries

2026 · Defan Xue, Yaqi Liu, et al. · IEEE International Conference on Acoustics Speech and Signal Processing

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning

2026 · Association for Artificial Intelligence 2026, Chen, Nuo, et al. · Underline Science Inc.

Works count: 8

Citation count: 2

H-index: 1

I10-index: