LLM Jailbreak Detection for (Almost) Free!

Large language models LLMs enhance security through alignment when widely used, but remain susceptible to jailbreak attacks capable of producing inappropriate content. Jailbreak detection methods show promise in mitigating jailbreak attacks through the assistance of other models or multiple model...

NVIDIA Triton Inference Server 输入验证错误漏洞

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. NVIDIA Triton Inference Server suffers from an input validation error vulnerability that originates from loading a misconfigured model, whi...

NVIDIA Triton Inference Server 缓冲区错误漏洞

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. NVIDIA Triton Inference Server suffers from an out-of-bounds write vulnerability that can be exploited by attackers to cause a denial of...

NVIDIA Triton Inference Server 输入验证错误漏洞

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. NVIDIA Triton Inference Server suffers from an input validation error vulnerability that stems from an improper input validation issue in t...

NVIDIA Triton Inference Server 访问控制错误漏洞

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. An access control error vulnerability exists in NVIDIA Triton Inference Server, which can be exploited by attackers to cause memory...

NVIDIA Triton Inference Server 操作系统命令注入漏洞

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. NVIDIA Triton Inference Server suffers from an operating system command injection vulnerability that stems from the Python backend not...

PT-2025-38283

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Description: The NVIDIA Triton Inference Server is susceptible to a denial-of-service condition triggered by loading a misconfigured model. Exploitation of this issue could lead t...

PT-2025-38129

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server versions prior to 25.08 Description: NVIDIA Triton Inference Server contains a vulnerability in the Python backend that allows for remote code execution. An attacker can exploit this by manipulating the model na...

Security Bulletin: NVIDIA Triton Inference Server - September 2025

NVIDIA has released a software update for NVIDIA Triton Inference Server to address the issue disclosed in this bulletin. To protect your system, install the latest release from the Triton Inference Server Releases page on GitHub, and view the Secure Deployment Considerations Guide. Go to NVIDIA...

Side-Channel Inference of User Activities in AR/VR Using GPU Profiling

Over the past decade, AR/VR devices have drastically changed how we interact with the digital world. Users often share sensitive information, such as their location, browsing history, and even financial data, within third-party apps installed on these devices, assuming a secure environment...

CVE-2025-47416

A vulnerability exists in the ConsoleFindCommandMatchList function in libsymproc. so imported by ctpd that may lead to unauthorized execution of an attacker-defined file that gets prioritized by the ConsoleFindCommandMatchList. A third-party researcher discovered that the...

CVE-2025-47416 ConsoleFindCommandMatchList

A vulnerability exists in the ConsoleFindCommandMatchList function in libsymproc. so imported by ctpd that may lead to unauthorized execution of an attacker-defined file that gets prioritized by the ConsoleFindCommandMatchList. A third-party researcher discovered that the...

Backdoor Attacks and Defenses in Computer Vision Domain: a Survey

Backdoor trojan attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly growing literature on backdoor attacks and defenses in the...

PT-2025-45525

Name of the Vulnerable Software and Affected Versions SuiteCRM versions 8.0.0 through 8.9.0 Description SuiteCRM is an open-source Customer Relationship Management CRM software application. A time-based blind SQL Injection flaw exists in versions 8.9.0 and below. This issue allows an authenticate...

Malicious code in com.unity.ai.inference (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=-...

MAL-2025-41955 Malicious code in com.unity.ai.inference (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=-...

Linux Distros Unpatched Vulnerability : CVE-2009-0654

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Tor 0.2.0.28, and probably 0.2.0.34 and earlier, allows remote attackers, with control of an entry router and an exit router, to confirm that a sender and...

(Pwn2Own) NVIDIA Triton Inference Server IPC Push Out-Of-Bounds Write Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of NVIDIA Triton Inference Server. Authentication is not required to exploit this vulnerability. The specific flaw exists within the processing of IPC messages. A crafted IPC Push request can trigger a...

(Pwn2Own) NVIDIA Triton Inference Server LoadFromSharedMemory Out-Of-Bounds Read Information Disclosure Vulnerability

This vulnerability allows remote attackers to disclose sensitive information on affected installations of NVIDIA Triton Inference Server. Authentication is not required to exploit this vulnerability. The specific flaw exists within the LoadFromSharedMemory function. The issue results from the lac...

NVIDIA Triton Inference Server Denial of Service Vulnerability (CNVD-2025-20006)

NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. NVIDIA Triton Inference Server has a denial of service vulnerability that can be exploited by an attacker to cause a denial of service...