3 papers
cs.CR2026
ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
Ningyuan He, Ronghong Huang, Qianqian Tang +3
In-context learning (ICL) has become a powerful, data-efficient paradigm for text classification using large language models. However, its robustness against realistic adversarial…
cs.CR2026
Okara: Detection and Attribution of TLS Man-in-the-Middle Vulnerabilities in Android Apps with Foundation Models
Haoyun Yang, Ronghong Huang, Yong Fang +4
Transport Layer Security (TLS) is fundamental to secure online communication, yet vulnerabilities in certificate validation that enable Man-in-the-Middle (MitM) attacks remain a pe…
cs.CR2024
Shining Light into the Tunnel: Understanding and Classifying Network Traffic of Residential Proxies
Ronghong Huang, Dongfang Zhao, Xianghang Mi +1
Emerging in recent years, residential proxies (RESIPs) feature multiple unique characteristics when compared with traditional network proxies (e.g., commercial VPNs), particularly,…