2 papers
cs.CL2025
Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers
Eugene Jang, Kimin Lee, Jin-Woo Chung +2
Tokenization is a crucial step that bridges human-readable text with model-readable discrete tokens. However, recent studies have revealed that tokenizers can be exploited to elici…
cs.CR2025
When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs
Hanna Kim, Minkyoo Song, Seung Ho Na +2
Recent advancements in Large Language Models (LLMs) have established them as agentic systems capable of planning and interacting with various tools. These LLM agents are often pair…