Jev models convert open-ended context into structured outputs, such as Boolean values, categories, scores or confidence levels, that applications use for branching, routing and policy enforcement.
Hostile context can redirect decisions in Jev-powered applications
JevProbe traced attacker-controlled inputs through structured model judgments and found decision changes across most of 228 tested applications.
Research Lab
Yang Luo · Tiantian Ji · Zifeng Kang · Yucheng Wang · Yong Liu · Zhiyi Yin · +1 more
Key Laboratory of Trustworthy Distributed Computing and Service (MoE) · Beijing University of Posts and Telecommunications · Zhongguancun Laboratory · Institute of Computing Technology, Chinese Academy of Sciences
Research Digest··2 min read
Luo and colleagues study a security failure they call Jev Program Decision Hijacking, in which untrusted context manipulates a Jev model into returning a structurally valid but semantically misleading judgment.
§