BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS

In this paper, we endeavor to address the challenges of backdoor attacks countermeasures in black-box scenarios, thereby fortifying the security of inference under MLaaS. We first categorize backdoor triggers from a new perspective, i.e., their impact on the patched area, and divide them into:...

PT-2025-32159 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Description: NVIDIA Triton Inference Server contains an issue in the Python backend that could allow an attacker to cause an out-of-bounds write. Successful exploitation of this...

PT-2025-32169 · Nvidia · Nvidia Triton Inference Server +1

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Tensor RT backend affected versions not specified Description: The NVIDIA Triton Inference Server and its Tensor RT backend contain an issue where an attacker can trigger an...

PT-2025-32150 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server versions prior to 25.07 Description: NVIDIA Triton Inference Server contains a vulnerability in the HTTP server that allows an attacker to initiate a reverse shell by sending a crafted HTTP request. Successful...

PT-2025-32161 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Description: NVIDIA Triton Inference Server contains an issue where multiple requests can cause a double free when a stream is cancelled before processing. Successful exploitation...

PT-2025-32160 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server for Windows and Linux affected versions not specified Description: The NVIDIA Triton Inference Server contains a flaw that allows a user to trigger a divide-by-zero error by submitting a malformed request...

PT-2025-31924

Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server versions prior to 25.07 Description NVIDIA Triton Inference Server contains a flaw where an attacker can trigger a stack overflow through crafted HTTP requests. Successful exploitation could lead to remote code...

PT-2025-32168 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Description: The NVIDIA Triton Inference Server contains an issue in the Python backend that allows an attacker to cause an out-of-bounds read by manipulating shared memory data. ...

PT-2025-31845 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server versions prior to 25.07 Description: NVIDIA Triton Inference Server contains a vulnerability in the Python backend that allows an attacker to cause an out-of-bounds write by sending a specially crafted request...

PT-2025-32165 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Description: NVIDIA Triton Inference Server contains an issue where an attacker could cause an integer overflow through a crafted input. A successful exploit may lead to a denial ...

PT-2025-32167 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server for Windows and Linux affected versions not specified Description: NVIDIA Triton Inference Server contains an issue where a user can trigger a segmentation fault by submitting an invalid request that causes...

PT-2025-32166 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server for Windows and Linux affected versions not specified Description: NVIDIA Triton Inference Server is susceptible to an integer overflow triggered by specially crafted inputs. Successful exploitation of this issu...

PT-2025-32164 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server for Windows and Linux affected versions not specified Description: The NVIDIA Triton Inference Server contains a flaw that allows an attacker to trigger uncontrolled recursion with a crafted input. Successful...

PT-2025-32162 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Description: NVIDIA Triton Inference Server is susceptible to an integer overflow or wraparound condition when processing invalid requests. This can result in a segmentation fault...

Security Bulletin: NVIDIA Triton Inference Server - August 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...

PT-2025-32163 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Description: The NVIDIA Triton Inference Server contains an issue where an attacker can cause an integer overflow or wraparound by submitting an invalid request. This can lead to ...

Cascading and Proxy Membership Inference Attacks

A Membership Inference Attack MIA assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or non-adaptive, depending on whether the adversary is allowed...

Program Analysis for High-Value Smart Contract Vulnerabilities: Techniques and Insights

A widespread belief in the blockchain security community is that automated techniques are only good for detecting shallow bugs, typically of small value. In this paper, we present the techniques and insights that have led us to repeatable success in automatically discovering high-value smart...

Hot-Swap MarkBoard: an Efficient Black-Box Watermarking Approach for Large-Scale Model Distribution

Recently, Deep Learning DL models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property IP risks, as models are distributed on numerous local devices, making them...

LoRA-Leak: Membership Inference Attacks against LoRA Fine-Tuned Language Models

Language Models LMs typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation LoRA has gained the most widespread use in LM fine-tuning due to its lightweight computational cost...