LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems

The increasing complexity and scale of the Internet of Things IoT have made security a critical concern. This paper presents a novel Large Language Model LLM-based framework for comprehensive threat detection and prevention in IoT environments. The system integrates lightweight LLMs fine-tuned on...

A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network

Large Language Models LLMs have achieved remarkable success across a wide range of applications. However, individual LLMs often produce inconsistent, biased, or hallucinated outputs due to limitations in their training corpora and model architectures. Recently, collaborative frameworks such as th...

NVIDIA TensorRT-LLM python executor code issue vulnerability

NVIDIA TensorRT-LLM is a high-performance inference acceleration library from NVIDIA for defining, optimizing, and executing inference in production environments for large language models LLMs. A code issue vulnerability exists in NVIDIA TensorRT-LLM that stems from insufficient data validation a...

xAI Dev Leaks API Key for Private SpaceX, Tesla LLMs

An employee at Elon Musk's artificial intelligence company xAI leaked a private key on GitHub that for the past two months could have allowed anyone to query private xAI large language models LLMs which appear to have been custom made for working with internal data from Musk's companies, includin...

optimum-nvidia (>=0.1.0b5, <=0.1.0b6) potentially affected by CVE-2025-23254 via tensorrt-llm (0.9.0.dev2024031900)

tensorrt-llm PYPI version 0.9.0.dev2024031900 is affected by a known vulnerability. The following packages have a transitive dependency on tensorrt-llm and may be impacted: - optimum-nvidia =0.1.0b5, =0.1.0b6 Source cves: CVE-2025-23254 Source advisory: SNYK:PYTHON-TENSORRTLLM-10255186...

Deserialization of Untrusted Data

Overview tensorrt-llm is a TensorRT-LLM: A TensorRT Toolbox for Large Language Models Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the ZeroMqQueue class in executor.py. An attacker can execute code, disclose information, and tamper with data by gaining...

CVE-2025-23254

NVIDIA TensorRT-LLM for any platform contains a vulnerability in python executor where an attacker may cause a data validation issue by local access to the TRTLLM server. A successful exploit of this vulnerability may lead to code execution, information disclosure and data tampering...

CVE-2025-23254

NVIDIA TensorRT-LLM (TensorRT-LLM Python executor) contains a data-validation vulnerability that can be exploited with local access to the TRTLLM server to achieve code execution, information disclosure, and data tampering. The CVE-2025-23254 entries across NVD/CVE lists describe a Python-executo...

CVE-2025-23254

NVIDIA TensorRT-LLM for any platform contains a vulnerability in python executor where an attacker may cause a data validation issue by local access to the TRTLLM server. A successful exploit of this vulnerability may lead to code execution, information disclosure and data tampering...

CVE-2025-23254

NVIDIA TensorRT-LLM for any platform contains a vulnerability in python executor where an attacker may cause a data validation issue by local access to the TRTLLM server. A successful exploit of this vulnerability may lead to code execution, information disclosure and data tampering...

NVIDIA TensorRT-LM Code Issues and Vulnerabilities

NVIDIA TensorRT-LLM is a high-performance inference acceleration library from NVIDIA for defining, optimizing, and executing inference in production environments for large language models LLMs. A code issue vulnerability exists in NVIDIA TensorRT-LLM that stems from insufficient data validation a...

PT-2025-18651

Name of the Vulnerable Software and Affected Versions NVIDIA TensorRT-LLM affected versions not specified Description The issue concerns a data validation problem in the python executor of NVIDIA TensorRT-LLM, which can be exploited by an attacker with local access to the TRTLLM server. A...

CVE-2025-23254: Deserialization of Untrusted Data

NVIDIA TensorRT-LLM for any platform contains a vulnerability in python executor where an attacker may cause a data validation issue by local access to the TRTLLM server. A successful exploit of this vulnerability may lead to code execution, information disclosure and data tampering...

decoding (0.1.1), lmcache-vllm (0.6.2.3) +2 more potentially affected by CVE-2025-32444 via vllm (0.6.2)

vllm PYPI version 0.6.2 is affected by a known vulnerability. The following packages have a transitive dependency on vllm and may be impacted: - decoding 0.1.1 - lmcache-vllm 0.6.2.3 - oat-llm =0.0.1, =0.1.0, =0.1.1 Source cves: CVE-2025-32444 Source advisory: OSV:PYSEC-2025-42...

happy-vllm (>=0.9.0, <=1.1.1), llumnix (0.0.2) +2 more potentially affected by CVE-2025-32444 via vllm (0.4.2)

vllm PYPI version 0.4.2 is affected by a known vulnerability. The following packages have a transitive dependency on vllm and may be impacted: - happy-vllm =0.9.0, =0.0.83, =0.1.0 Source cves: CVE-2025-32444 Source advisory: OSV:PYSEC-2025-42...

llm-engines (>=0.0.1, <=0.0.2) potentially affected by CVE-2025-32444 via vllm (0.5.1)

vllm PYPI version 0.5.1 is affected by a known vulnerability. The following packages have a transitive dependency on vllm and may be impacted: - llm-engines =0.0.1, =0.0.2 Source cves: CVE-2025-32444 Source advisory: OSV:PYSEC-2025-42...

docext (>=0.1.10, <=0.1.14), genlm-backend (>=0.1.1, <=0.1.3) +2 more potentially affected by CVE-2025-46560 via vllm (>=0.8.3, <=0.8.4)

vllm PYPI version =0.8.3, =0.1.10, =0.1.1, =0.1.1, =0.2.4 - txagent 0.1.3 Source cves: CVE-2025-46560 Source advisory: MEND:CVE-2025-46560...

CVE-2025-46560

CVE-2025-46560 affects vLLM 0.8.0–0.8.4, where the multimodal tokenizer’s input preprocessing uses placeholder tokens replaced by repeated tokens. The replacement logic relies on inefficient list concatenation, yielding quadratic time complexity (O(n²)) and enabling resource exhaustion via crafte...

PT-2025-18649

Name of the Vulnerable Software and Affected Versions NVIDIA TensorRT-LLM affected versions not specified NVIDIA vGPU software affected versions not specified Description The issue concerns a data validation problem in the python executor of NVIDIA TensorRT-LLM, which can be exploited by an...

docext (>=0.1.10, <=0.1.14), genlm-backend (>=0.1.1, <=0.1.3) +2 more potentially affected by CVE-2025-46560 via vllm (>=0.8.3, <=0.8.4)

vllm PYPI version =0.8.3, =0.1.10, =0.1.1, =0.1.1, =0.2.4 - txagent 0.1.3 Source cves: CVE-2025-46560 Source advisory: OSV:GHSA-VC6M-HM49-G9QG...