Unverified50% confidenceFactExact time
The core of linguistic illegibility attacks lies in exploiting the form of expression itself to create blind spots in understanding, with attackers deceiving the defensive layers outside the model rather than the model itself.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAny text originating from external, untrusted sources should be treated as a potential attack vector before entering a large language model.76% similarUnverifiedPrompt Injection攻击难以防御的根本原因是语言模型无法区分系统指令和用户数据，因为它们都只是输入文本的一部分72% similarUnverifiedTypical techniques for linguistic illegibility attacks include replacing sensitive vocabulary with Unicode variant characters, mixing multiple languages, using low-resource languages to bypass filters, and fragmenting harmful intent across multiple conversation turns.72% similarUnverified自然语言作为攻击载体使得攻击样本几乎无法被签名检测，每次攻击可用不同措辞表达相同恶意意图72% similarUnverifiedIntroducing large language models to give the system semantic understanding capabilities enables it to understand the deceptive differences in phrasing between scam scripts and system warnings.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/933157API
curl https://kongchang.com/api/v1/knowledge/claims/933157MCP
get_claim(id=933157)