EUVD-2025-7031

Malicious code in bioql PyPI...

MAL-2025-47017 Malicious code in image_classification (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 33e5c05f2c70291fde5a4ace56b3aa015c8c407695c02395a9a4336285e964a3 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Malicious Package

Overview imageclassification is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

Malicious code in image_classification (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 33e5c05f2c70291fde5a4ace56b3aa015c8c407695c02395a9a4336285e964a3 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Adversarial Attacks to Image Classification Systems Using Evolutionary Algorithms

Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an approach to generate adversarial attacks against image...

Hashed Watermark As a Filter: Defeating Forging and Overwriting Attacks in Weight-Based Neural Network Watermarking

As valuable digital assets, deep neural networks necessitate robust ownership protection, positioning neural network watermarking NNW as a promising solution. Among various NNW approaches, weight-based methods are favored for their simplicity and practicality; however, they remain vulnerable to...

Counterfactual Influence As a Distributional Quantity

Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metric to study memorization, quantifying how the model's prediction for a sample changes depending on the sample's...

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference

Differential privacy DP auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work introduces one-run auditing approaches that effectively audit DP-SGD...

Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturing

In the semiconductor sector, due to high demand but also strong and increasing competition, time to market and quality are key factors in securing significant market share in various application areas. Thanks to the success of deep learning methods in recent years in the computer vision domain,...

AGATE: Stealthy Black-Box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence AI models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution OoD data as backdoor watermarks and retrain the original model for...

Arbitrary File Write via Archive Extraction (Zip Slip)

Overview gluoncv is a Gluon CV Toolkit Affected versions of this package are vulnerable to Arbitrary File Write via Archive Extraction Zip Slip via the fromcsv function in ImageClassificationDataset. An attacker can overwrite files on the victim's system by using this function to extract maliciou...

CVE-2024-12216

The CVE-2024-12216 issue affects dmlc/gluon-cv 0.10.0, specifically ImageClassificationDataset.from_csv(). The vulnerability arises because tar.gz files downloaded from URLs are extracted without proper sanitization, enabling TarSlip via path traversal or faked symlinks to overwrite arbitrary fil...

Octopii - An AI-powered Personal Identifiable Information (PII) Scanner

Octopii is an open-source AI-powered Personal Identifiable Information PII scanner that can look for image assets such as Government IDs, passports, photos and signatures in a directory. Working Octopii uses Tesseract's Optical Character Recognition OCR and Keras' Convolutional Neural Networks CN...

In0ri - Defacement Detection With Deep Learning

In0ri is a defacement detection system utilizing a image-classification convolutional neural network. Introduction When monitoring a website, In0ri will periodically take a screenshot of the website then put it through a preprocessor that will resize the image down to 250x250px and numericalize t...

abmarl (>=0.1.1 <=0.1.3), agrothon (>=1.1.5 <=1.3.2) +94 more potentially affected by CVE-2021-29532 via tensorflow (>=2.4.0 <=2.4.2)

tensorflow PYPI version =2.4.0, =0.1.1, =1.1.5, =2.1.0, =0.7.0, =0.0.1, =0.0.6, =0.1.0, =1.4.0, =1.2.2, =20210221.0.0, =0.7.2, =0.7.4 and more Source cves: CVE-2021-29532 Source advisory: OSV:PYSEC-2021-169...

In the picture, the added noise will be able to fool Google's best image recognition AI-vulnerability warning-the black bar safety net

! Recently, a group from the University of Washington, network security lab NSL's computer experts found that a malicious attacker can trick Google's CloudVision API, this will cause the API to the user-submitted images were incorrectly classified. In recent years, based on the AI of the image...