Unverified50% confidenceFactExact time
Typical 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.
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.72% similarUnverifiedThe 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.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% similarUnverifiedIn production environments, users may input content containing ambiguity, typos, mixed multilingual text, or even malicious injections (Prompt Injection).71% similarUnverifiedCross-lingual jailbreaking exploits the asymmetry between a model's concept space and its language space, as the learning of safety-refusal behavior is highly language-specific.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/933158API
curl https://kongchang.com/api/v1/knowledge/claims/933158MCP
get_claim(id=933158)