A Robust Cross-Domain IDS Using BiGRU-LSTM-Attention for Medical and Industrial IoT Security

The increased Internet of Medical Things IoMT and the Industrial Internet of Things IIoT interconnectivity has introduced complex cybersecurity challenges, exposing sensitive data, patient safety, and industrial operations to advanced cyber threats. To mitigate these risks, this paper introduces ...

Mitigating Jailbreaks with Intent-Aware LLMs

Despite extensive safety-tuning, large language models LLMs remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose Intent-FT, a simple and lightweight fine-tuning approach that...

Zero Trust + AI: Privacy in the Age of Agentic AI

We used to think of privacy as a perimeter problem: about walls and locks, permissions, and policies. But in a world where artificial agents are becoming autonomous actors — interacting with data, systems, and humans without constant oversight — privacy is no longer about control. It's about trus...

NVIDIA Triton Inference Server Python Backend Out-of-Bounds Write Vulnerability

Triton Inference Server is a high-performance inference service engine developed by NVIDIA, designed for AI model deployment in production environments, with support for a variety of frameworks TensorFlow, PyTorch, ONNX, etc. and optimized inference performance for GPUs and CPUs. An out-of-bounds...

NVIDIA Triton Inference Server Code Execution Vulnerability

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. A code execution vulnerability exists in NVIDIA Triton Inference Server, which can be exploited by attackers to execute arbitrary code, cau...

NVIDIA Triton Inference Server Integer Overflow Vulnerability

Triton Inference Server is a high-performance inference service engine developed by NVIDIA, designed for AI model deployment in production environments, with support for a variety of frameworks TensorFlow, PyTorch, ONNX, etc. and optimized inference performance for GPUs and CPUs. An integer...

NVIDIA Triton Inference Server Code Execution Vulnerability (CNVD-2025-20011)

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. A code execution vulnerability exists in NVIDIA Triton Inference Server, which can be exploited by attackers to execute arbitrary code, cau...

NVIDIA Triton Inference Server Python Out-of-Bounds Read Vulnerability

Triton Inference Server is a high-performance inference service engine developed by NVIDIA, designed for AI model deployment in production environments, with support for a variety of frameworks TensorFlow, PyTorch, ONNX, etc. and optimized inference performance for GPUs and CPUs. An out-of-bounds...

NVIDIA Triton Inference Server Integer Overflow Vulnerability

Triton Inference Server is a high-performance inference service engine developed by NVIDIA, designed for AI model deployment in production environments, with support for a variety of frameworks TensorFlow, PyTorch, ONNX, etc. and optimized inference performance for GPUs and CPUs. An integer...

NVIDIA Triton Inference Server Denial of Service Vulnerability (CNVD-2025-20009)

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. A denial of service vulnerability exists in NVIDIA Triton Inference Server, which stems from an invalid request that could result in a...

NVIDIA Triton Inference Server Stack Overflow Vulnerability

Triton Inference Server is a high-performance inference service engine developed by NVIDIA, designed for AI model deployment in production environments, with support for a variety of frameworks TensorFlow, PyTorch, ONNX, etc. and optimized inference performance for GPUs and CPUs. A stack overflow...

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-Cache in LLM Inference

The Key-Value KV cache, which stores intermediate attention computations Key and Value pairs to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model LLM inference. However, this efficiency optimization introduces significant yet underexplored privacy risk...

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to integer overflow. This vulnerability allows a malicious actor to trigger a service failure.

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server previously known as TensorRT Inference Server is related to a numerical overflow issue. Exploiting this vulnerability could allow an attacker to cause service failures...

The vulnerability of the software for deploying and executing AI models developed with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) allows a malicious actor to trigger a service failure. This vulnerability is related to zero-division errors.

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server formerly TensorRT Inference Server is related to division by zero errors. Exploiting this vulnerability can allow a malicious actor to trigger a service failure by sending a specially crafted request...

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to integer overflow. This vulnerability allows a malicious actor to trigger a service failure.

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server previously known as TensorRT Inference Server is related to a numerical overflow issue. Exploiting this vulnerability could allow an attacker to cause service failures...

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to integer overflow. This vulnerability allows a malicious actor to trigger a service failure.

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server previously known as TensorRT Inference Server is related to a numerical overflow issue. Exploiting this vulnerability could allow an attacker to cause service failures...

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to integer overflow. This vulnerability allows a malicious actor to trigger a service failure.

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server previously known as TensorRT Inference Server is related to a numerical overflow issue. Exploiting this vulnerability could allow an attacker to cause service failures...

The vulnerability of the software for deploying and executing AI models developed by NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to a memory reclamation error. This vulnerability allows attackers to trigger a service failure.

The vulnerability of the NVIDIA Triton Inference Server previously known as TensorRT Inference Server software for deploying and executing AI models is related to a memory reclamation error. Exploiting this vulnerability could allow a remote attacker to cause a service failure...

The vulnerability of the software for deploying and executing AI models with NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) lies in its ability to allow numerical overflow, which can lead to service interruptions for attackers.

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server previously known as TensorRT Inference Server is related to the possibility of numerical overflow. Exploiting this vulnerability could allow a malicious actor to cause service failures...

The vulnerability of the software for deploying and executing AI models developed by NVIDIA Triton Inference Server (previously known as TensorRT Inference Server) relates to buffer overflows in dynamic memory. This vulnerability allows attackers to cause system failures, gain unauthorized access to protected information, and execute arbitrary code.

The vulnerability of the software for deploying and executing NVIDIA Triton Inference Server previously known as TensorRT Inference Server is related to buffer overflow in dynamic memory. Exploiting this vulnerability can allow a remote attacker to cause service failures, gain unauthorized access...