vLLM PageAttention Disclosure

The vulnerability of the PageAttention mechanism in the library for working with Large Language Models LLM vLLM relates to the disclosure of information due to timing mismatches. Exploiting this vulnerability could allow a malicious actor, operating remotely, to disclose the protected information...

EUVD-2025-16189

Malicious code in bioql PyPI...

Timing Side-channel Attacks

vllm is vulnerable to Timing side-channel attacks. The vulnerability is due to timing discrepancies during the prefill phase by the PageAttention mechanism reusing matching prefix chunks, which speeds up token generation and allows an attacker to infer prompt similarity or presence...

CVE-2025-46570

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

CVE-2025-46570

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

CVE-2025-46570 vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

CVE-2025-46570

The CVE-2025-46570 entry concerns vLLM (inference/serving engine). The concrete detail across connected records shows a vulnerability in the PageAttention-based prefill path: when a new prompt is processed, a matching prefix chunk can accelerate prefill, creating timing differences (TTFT) that co...

CVE-2025-46570: Observable Timing Discrepancy

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

vLLM security vulnerabilities

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A security vulnerability exists in vLLM versions prior to 0.9.0 that stems from a timing difference in the PageAttention mechanism that could be exploited...

Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching

This issue arises from the prefix caching mechanism, which may expose the system to a timing side-channel attack. Description When a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First...

PT-2025-54995

Уязвимость механизма PageAttention библиотеки для работы с большими языковыми моделями LLM vLLM связана с раскрытием информации из-за несоответствия во времени. Эксплуатация уязвимости может позволить нарушителю, действующему удаленно, раскрыть защищаемую информацию...