arXiv Machine Learning
SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 5
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels
arXiv:2608. 02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens.
arXiv AI
Jun 30
Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs
arXiv:2606. 28479v1 Announce Type: cross Abstract: CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD.
arXiv AI
Sep 1
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
arXiv:2604.27426v2 Announce Type: replace-cross Abstract: Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although "local...
arXiv AI
Jun 15
From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models
arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.
arXiv AI
Sep 10
Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces
The paper introduces an attack that reconstructs text generated by locally hosted large language models by monitoring CPU cache activity during detokenization. It uses Flush+Reload on shared tokenizer code to time decoding, then Prime+Probe to capture token‑dependent cache traces, followed by a clustering‑and‑language‑model pipeline to recover the output text. The method is evaluated across various datasets, hardware, inference frameworks, and model families, successfully retrieving semantically accurate outputs from real‑world local LLM deployments, including agentic systems.
arXiv AI
Aug 19
The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges
The paper introduces LeakGauge, a method that appends a suffix to a model’s input to gauge the risk of context leakage before decoding. By mapping prefill token probabilities to an attack‑risk score, LeakGauge achieves high AUROC (0.944–0.996) across 11 large language models, including GLM‑5.2 and Kimi‑K3, and remains robust to language changes and different attack styles. The approach also demonstrates sensitivity to internal leakage directions and can be implemented with fewer than 0.5K additional parameters and minimal latency.