arXiv (All)
open access
Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces
We present a new attack that reconstructs the text generated by locally hosted LLMs by observing CPU cache activity during detokenization. Unlike prior attacks that rely on deployment-specific assumptions, such as shared data memory, CPU offloading, or Mixture-of-Experts architectures, our approach
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SteganoBackdoor: Evading Data-Poisoning Defenses via Steganographic Backdoors#1034684
- Weaponizing Ground Truth: Data Poisoning Attacks by Exploiting Boundary Misalignment Between Antivirus Software and Learning-Based Detectors#1105562
- Remote-Timer-as-a-Service: Efficient Microarchitectural Leakage in the Cloud with Remote Timers#463185
- Information Leakage Envelopes#216749
- Drishti: AI-Led Human-Directed Vulnerability Auditing for 5G Cores#622450
Record · ID 974776
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive