arXiv AI September 10, 2026 By Roy Weiss, Benyamin Konstantinov, Eitam Sheetrit, Tomer Simon, Yisroel Mirsky

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 23

HijackKV: New Threat in Position-Independent KV Cache Reuse

arXiv:2607. 19957v1 Announce Type: cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs).

By Yichi Zhang, Zhiqi Wang, Huan Zhang, Yuchen Yang

llms efficiency

arXiv Machine Learning

2d ago

SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs

arXiv:2609.38830v1 Announce Type: new Abstract: Sparse attention is widely used to accelerate long-context inference in modern large language models (LLMs), but its input-dependent execution behavior...

By Fahao Chen, Linkang Du, Jinhao Zhou, Peng Li, Zhou Su

llms efficiency safety

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...

By Zi Li, Tian Zhou, Wenze Li, Jingyu Hua, Yunlong Mao, Sheng Zhong

llms fine-tuning multimodal safety

arXiv Machine Learning

Jul 24

Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing

arXiv:2607. 20723v1 Announce Type: cross Abstract: This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models.

By Sadegh Majidi, Niloofar Mireshghallah, Kazem Taram

llms

arXiv AI

Sep 21

CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents

CIPL (Channel Inversion for Privacy Leakage) is a channel-aware framework designed to evaluate black-box privacy leakage in large language model agents. It models the leakage process through stages of sensitive source, selection, assembly, execution, observation, and extraction, assessing how selected sensitive units become attacker-recoverable outputs. Experiments across memory, retrieval, and tool-mediated targets, plus a live-agent case study, reveal that recoverability depends on factors beyond storage labels, such as observation surface, prompt alignment, retrieval depth, and provider behavior, and that a semantic audit can uncover disclosures missed by exact matching.

By Tao Huang, Guosen Wu, Guolong Zheng, Jiayang Meng, Chen Hou, Xu Yang, Xuechao Yang, Feng Xia

llms agents safety

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.

By Yongwan Jo, Jinyoung Park, Euihyun Lee, Dokyung Song

llms efficiency

One email a morning, machine-written

Related stories

HijackKV: New Threat in Position-Independent KV Cache Reuse

SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors

Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing

CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels