Andrew Paverd
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×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.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.CLRecentMay 14, 2026
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma +1 more
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.
View →