211 matches found
BackFed: an Efficient and Standardized Benchmark Suite for Backdoor Attacks in Federated Learning
Federated Learning FL systems are vulnerable to backdoor attacks, where adversaries train their local models on poisoned data and submit poisoned model updates to compromise the global model. Despite numerous proposed attacks and defenses, divergent experimental settings, implementation errors, a...
CVAT.ai CVAT 安全漏洞
CVAT.ai CVAT is an open source data processing tool from CVAT.ai. A security vulnerability exists in CVAT.ai CVAT versions 2.2.0 through 2.39.0, which stems from a lack of validation during the import process and could lead to a data leak...
DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?
Adversarial examples are small and often imperceptible perturbations crafted to fool machine learning models. These attacks seriously threaten the reliability of deep neural networks, especially in security-sensitive domains. Evasion attacks, a form of adversarial attack where input is modified a...
CVE-2024-53015 Use After Free in Computer Vision
Memory corruption while processing IOCTL command to handle buffers associated with a session...
CVE-2024-53015
CVE-2024-53015 describes a memory corruption issue in Qualcomm chipsets triggered when processing IOCTL commands to handle buffers for a session. The vulnerability affects IOCTL buffer handling code and is evidenced by multiple feeds (NVD and Red Hat advisories) reporting memory corruption withou...
CVE-2024-53015 Use After Free in Computer Vision
Memory corruption while processing IOCTL command to handle buffers associated with a session...
CVE-2025-48381
Computer Vision Annotation Tool CVAT is an interactive video and image annotation tool for computer vision. In versions starting from 2.4.0 to before 2.38.0, an authenticated CVAT user may be able to retrieve the IDs and names of all tasks, projects, labels, and the IDs of all jobs and quality...
CVE-2025-48381 CVAT has information disclosure via browsable API
Computer Vision Annotation Tool CVAT is an interactive video and image annotation tool for computer vision. In versions starting from 2.4.0 to before 2.38.0, an authenticated CVAT user may be able to retrieve the IDs and names of all tasks, projects, labels, and the IDs of all jobs and quality...
Computer Vision Annotation Tool 安全漏洞
Computer Vision Annotation Tool CVAT is a cvat.ai open source interactive video and image annotation tool for computer vision. A security vulnerability exists in Computer Vision Annotation Tool versions prior to 2.4.0 through 2.38.0, which stems from the possibility that an authenticated user may...
CVE-2025-48381: Insertion of Sensitive Information Into Sent Data
Computer Vision Annotation Tool CVAT is an interactive video and image annotation tool for computer vision. In versions starting from 2.4.0 to before 2.38.0, an authenticated CVAT user may be able to retrieve the IDs and names of all tasks, projects, labels, and the IDs of all jobs and quality...
CVE-2024-47172
Computer Vision Annotation Tool CVAT is an interactive video and image annotation tool for computer vision. An attacker with a CVAT account may retrieve certain information about any project, task, job or membership resource on the CVAT instance. The information exposed in this way is the same as...
CVE-2024-47064
Computer Vision Annotation Tool CVAT is an interactive video and image annotation tool for computer vision. If an attacker can trick a logged-in CVAT user into visiting a maliciously-constructed URL, they can initiate any API calls on that user's behalf. This gives the attacker temporary access t...
CVE-2022-33281
Memory corruption due to improper validation of array index in computer vision while testing EVA kernel without sending any frames...
CVE-2021-30046
VIGRA Computer Vision Library Version-1-11-1 contains a segmentation fault vulnerability in the impex.hxx readimageband function, in which a crafted file can cause a denial of service...
CVE-2025-21468 Out-of-bounds Write in Computer Vision
Memory corruption while reading response from FW, when buffer size is changed by FW while driver is using this size to write null character at the end of buffer...
CVE-2025-21467 Out-of-bounds Write in Computer Vision
Memory corruption while reading the FW response from the shared queue...
CVE-2025-21467 Out-of-bounds Write in Computer Vision
Memory corruption while reading the FW response from the shared queue...
CVE-2025-21462 Out-of-bounds Write in Computer Vision
Memory corruption while processing an IOCTL request, when buffer significantly exceeds the command argument limit...
