The Rise of the LLM AI Scrapers: What It Means for Bot Management

Explore the rise of LLM AI scrapers and learn how to adapt to growing bot traffic with data-backed insights from our research...

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...

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 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...

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...

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...

PT-2025-18649 · Nvidia · Nvidia Tensorrt-Llm +1

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...

NVIDIA TensorRT-LLM 代码问题漏洞

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...

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...

GHSA-HJ4W-HM2G-P6W5 vLLM Vulnerable to Remote Code Execution via Mooncake Integration

Impacted Deployments Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable. Description vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were...

Akamai Firewall for AI: Get Powerful Protection for New LLM App Threats

Protect against LLM attacks such as prompt injection, exfiltration and extraction, and toxic AI outputs with Akamai Firewall for AI...

Adversarial Attacks on LLM-As-A-Judge Systems: Insights from Prompt Injections

LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content author attacks from system prompt attacks and evaluate five models Gemma 3.27B Gemma 3.4B Llama 3.2 3B GPT 4 and Clau...

CVE-2025-3578

A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments. In addition, it would be possible to cause bugs that would result in the...

CVE-2025-3578 Adversarial Input Handling Vulnerability in AiDex

A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments. In addition, it would be possible to cause bugs that would result in the...

CVE-2025-3578 Adversarial Input Handling Vulnerability in AiDex

A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments. In addition, it would be possible to cause bugs that would result in the...