Jun Sakuma
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2ML×1NLP×1
Frequent co-authors
Research Timeline
2026
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
The paper introduces MetaBackdoor, a novel class of LLM backdoor attacks that exploits positional encoding (length-based triggers) rather than requiring modifications to the textual content.
Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
The paper introduces Neutral Prompting Attacks (NPA), a stealthy method showing that semantically benign prompts can covertly increase package hallucination in coding agents, creating new software supply chain risks.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.LGRecentMay 28, 2026
Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
The paper introduces Neutral Prompting Attacks (NPA), a stealthy method showing that semantically benign prompts can covertly increase package hallucination in coding agents, creating new software sup…
View →
cs.CRcs.CLRecentMay 14, 2026