Spore extracts private data from LLM memory with one query in black-box mode or ranked tokens in gray-box, outperforming prior attacks while bypassing defenses.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CR 3years
2026 3roles
background 2polarities
background 2representative citing papers
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
citing papers explorer
-
Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing
Spore extracts private data from LLM memory with one query in black-box mode or ranked tokens in gray-box, outperforming prior attacks while bypassing defenses.
-
An Independent Safety Evaluation of Kimi K2.5
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses