2417 matches found
PT-2025-26612 · Sensopart · Sensopart Visor Vision Sensors
Name of the Vulnerable Software and Affected Versions: Sensopart VISOR Vision Sensors versions prior to 2.10.0.2 Description: An issue was discovered that allows local users to perform unspecified actions with elevated privileges. Recommendations: For Sensopart VISOR Vision Sensors versions prior...
CVE-2023-50450: Improper Privilege Management
An issue was discovered in Sensopart VISOR Vision Sensors before 2.10.0.2 allows local users to perform unspecified actions with elevated privileges...
Sensopart VISOR Vision Sensors 安全漏洞
Sensopart VISOR Vision Sensors is a vision camera for factory automation from Sensopart, Germany. A security vulnerability exists in Sensopart VISOR Vision Sensors versions prior to 2.10.0.2, which originates from a local user who may perform privileged operations...
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...
Deep CNN Face Matchers Inherently Support Revocable Biometric Templates
One common critique of biometric authentication is that if an individual's biometric is compromised, then the individual has no recourse. The concept of revocable biometrics was developed to address this concern. A biometric scheme is revocable if an individual can have their current enrollment i...
NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
Vision-Language Models VLMs such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable to adversarial attacks, particularly in the image modality,...
Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
Large vision-language models LVLMs have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information. Therefore, it is important to detect whether an image is used t...
Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
Adversarial examples have attracted significant attention over the years, yet understanding their frequency-based characteristics remains insufficient. In this paper, we investigate the intriguing properties of adversarial examples in the frequency domain for the image classification task, with t...
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
The rapid advancement of vision-language models VLMs and their integration into embodied agents have unlocked powerful capabilities for decision-making. However, as these systems are increasingly deployed in real-world environments, they face mounting safety concerns, particularly when responding...
Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
With the growing integration of vision-language models VLMs, mobile agents are now widely used for tasks like UI automation and camera-based user assistance. These agents are often fine-tuned on limited user-generated datasets, leaving them vulnerable to covert threats during the training process...
Busting the Paper Ballot: Voting Meets Adversarial Machine Learning
We show the security risk associated with using machine learning classifiers in United States election tabulators. The central classification task in election tabulation is deciding whether a mark does or does not appear on a bubble associated to an alternative in a contest on the ballot. Barrett...
Theoretically Unmasking Inference Attacks against LDP-Protected Clients in Federated Vision Models
Federated Learning enables collaborative learning among clients via a coordinating server while avoiding direct data sharing, offering a perceived solution to preserve privacy. However, recent studies on Membership Inference Attacks MIAs have challenged this notion, showing high success rates...
The Safety Reminder: a Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language Models
As Vision-Language Models VLMs demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models LLMs, VLMs face unique vulnerabilities due to their multimodal...
SQL Injection Vulnerability in Multimedia Integrated Service Display System of Beijing Shenzhou Vision Han Technology Co., Ltd (CNVD-C-2025-321946)
Ltd. is a deep-rooted enterprise in the field of visualization. A SQL injection vulnerability exists in the multimedia integrated business display system of Beijing Divine Vision Han Technology Co. Ltd, which can be exploited by attackers to obtain sensitive information from the database...
SQL Injection Vulnerability in Multimedia Integrated Service Display System of Beijing Shenzhou Vision Han Technology Co., Ltd (CNVD-C-2025-319811)
Ltd. is a deep-rooted enterprise in the field of visualization. A SQL injection vulnerability exists in the multimedia integrated business display system of Beijing Divine Vision Han Technology Co. Ltd, which can be exploited by attackers to obtain sensitive information from the database...
DAVSP: Safety Alignment for Large Vision-Language Models Via Deep Aligned Visual Safety Prompt
Large Vision-Language Models LVLMs have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectivel...
SoK: Data Reconstruction Attacks against Machine Learning Models: Definition, Metrics, and Benchmark
Data reconstruction attacks, which aim to recover the training dataset of a target model with limited access, have gained increasing attention in recent years. However, there is currently no consensus on a formal definition of data reconstruction attacks or appropriate evaluation metrics for...
Attacking Attention of Foundation Models Disrupts Downstream Tasks
Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning. For this reason, models such as CLIP , DINO or Vision...
Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
Vision Language Models VLMs have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality triggers, leaving the crucial cross-modal fusion nature of...