23 citations · 66 across the 12 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.CR2026
ClaimMirage: When Self-Claims in Domain Names Change LLM Threat Judgments
Daiki Chiba, Hiroki Nakano, Takashi Koide
Short claims such as not-phishing or official can change how a large language model (LLM) judges a domain name, without explicit prompt-injection commands. We study this manipulati…
cs.CR2026
TIBlender: Early-Warning Threat Intelligence from Cross-Platform Social Media Evidence
Hiroki Nakano, Takashi Koide, Daiki Chiba
Cyber threat signals are fragmented across multiple social media platforms, yet no existing approach has fully automated their integration into actionable threat intelligence (TI)…
cs.CR2026
Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection
Takashi Koide, Hiroki Nakano, Daiki Chiba
Phishing sites continue to increase in number and sophistication. Recent work uses large language models (LLMs) to analyze URLs, HTML, and rendered content and determine whether a…