Search for: All records

Computer Vision models has increasingly been embedded into video software to recognize and classify things in the physical world. While this can provide a useful result it also opens the door to vulnerabilities through a physical attack. Using a printed-out generated image, individuals can exploit computer visions models to disguise their true intentions. A possible way to block and mitigate the problems is to detect and blur the entire image to try to allow the AI to inference the said image. 

In this paper, we document our findings from previous research and literature related to adversarial examples and object detection. Artificial Intelligence (AI) is an increasingly powerful tool in various fields, particularly in image classification and object detection. As AI becomes more advanced, new methods to deceive machine learning models, such as adversarial patches, have emerged. These subtle modifications to images can cause AI models to misclassify objects, posing a significant challenge to their reliability. This research builds upon our earlier work by investigating how small patches affect object detection on YOLOv8. Last year, we explored patterns within images and their impact on model accuracy. This study extends that work by testing how adversarial patches, particularly those targeting animal patterns, affect YOLOv8's ability to accurately detect objects. We also explore how untrained patterns influence the model’s performance, aiming to identify weaknesses and improve the robustness of object detection systems. 

This report will discuss and analyze the risks and challenges associated with smart home devices, focusing on vulnerabilities in commonly used products such as smart speakers, security cameras, thermostats, and lighting systems. As the adoption of smart home security grows globally, it has become clear that many users remain unaware of the associated security risks, leading to data breaches and potential privacy violations. This research evaluates the security features of these devices, the frequency of breaches, and common vulnerabilities. Using a mixed-methods approach—including a user survey, analysis of past cybersecurity incidents, and a detailed review of existing literature—this study assesses the current state of smart home device security. The findings aim to highlight gaps in user awareness, evaluate manufacturers’ protective measures, and provide recommendations for improving cybersecurity practices in smart home environments. 

Computer Vision models have increasingly been embedded into video software to recognize and classify things in the physical world. While this can provide a useful result it also opens the door to vulnerabilities through a physical attack. Using a printed-out generated image, individuals can exploit computer visions models to disguise their true intentions. A possible way to block and mitigate the problems is to detect and blur the entire image to try to allow the AI to inference the said image. 

As cyber threats grow in both frequency and sophistication, traditional cybersecurity measures struggle to keep pace with evolving attack methods. Artificial Intelligence (AI) has emerged as a powerful tool for enhancing threat detection, prevention, and response. AI-driven security systems offer the ability to analyze vast amounts of data in real-time, recognize subtle patterns indicative of cyber threats, and adapt to new attack strategies more efficiently than conventional approaches. However, despite AI’s potential, challenges remain regarding its effectiveness, ethical implications, and risks of adversarial manipulation. This research investigates the strengths and limitations of AI-driven cybersecurity by comparing AI-based security tools with traditional methods, identifying key advantages and vulnerabilities, and exploring ethical considerations. Additionally, a survey of cybersecurity professionals was conducted to assess expert opinions on AI’s role, effectiveness, and potential risks. By combining these insights with experimental testing and a comprehensive review of existing literature, this study provides a nuanced understanding of AI’s impact on cybersecurity and offers recommendations for optimizing its integration into modern security infrastructures. 

This study examines how artificial intelligence (AI) can help with voice phishing (vishing) attacks, with a particular emphasis on deepfake technologies and AI-driven voice synthesis. It examines the strategies used by cybercriminals, assesses the effectiveness of the present defenses, and identifies difficulties in identifying and preventing such attacks. The results show that to combat the increasing complexity of vishing strategies, there is an urgent need for sophisticated detection systems and preventive actions. Future directions include the creation of cooperative policy frameworks to control the misuse of AI and easily accessible solutions for small enterprises. 

Adversarial patches represent a critical vulnerability in computer vision systems, as they are specifically created in order to deceive object detection algorithms, which can compromise their reliability in real-world applications. This research investigates the impact of adversarial patches on object detection models and proposes a novel mitigation strategy to address this challenge. The study's primary objective was to design a comprehensive framework that integrates adversarial patch detection with image restoration. To achieve this, a YOLOv8-based detection framework was employed, trained on a specialized dataset of adversarial patches to ensure high detection accuracy. Upon identification of patches, advanced inpainting techniques utilizing AI models were applied to mask and fill the affected areas, restoring the image with expected content. The methodology combines the precision of object detection with the generative capabilities of modern inpainting algorithms, ensuring minimal disruption to the visual integrity of the image. This work contributes to the field of adversarial robustness by providing a comprehensive approach that integrates detection, masking, and content restoration. The results highlight the potential of AI-driven solutions to enhance the resilience of object detection systems against adversarial attacks, paving the way for safer deployment of vision-based technologies in critical domains such as autonomous vehicles, surveillance, and medical imaging. 

In this paper, we documented our findings from previous research and literature related to adversarial examples and object detection. Artificial Intelligence (AI) is an increasingly powerful tool in various fields, particularly in image classification and object detection. As AI becomes more advanced, new methods to deceive machine learning models, such as adversarial perturbations, have emerged. These subtle modifications to images can cause AI models to misclassify objects, posing a significant challenge to their reliability. This research builds upon our earlier work by investigating how small perturbations affect object detection on YOLOv8. Last year, we explored patterns within images and their impact on model accuracy. This study will extend that by testing how adversarial perturbations, particularly those targeting animal patterns, affect YOLO v8's ability to accurately detect objects. We will also explore how untrained patterns influence the model’s performance, aiming to identify weaknesses and improve the robustness of object detection systems. 

Deepfake technology presents a significant challenge to cybersecurity. These highly sophisticated AI-generated manipulations can compromise sensitive information and erode public trust, privacy, and security. This has led to broader societal impacts, including decreased trust and confidence in digital communications. This paper will discuss public knowledge, understanding, and perception of AI-generated deepfakes, which was obtained through an online survey that measured people's ability to identify video, audio, and images of deepfakes. The findings will highlight the public's knowledge and perception of deepfakes, the risks that deepfake media presents, and the vulnerabilities to detection and prevention. This awareness will lead to stronger defense strategies and enhanced cybersecurity measures that will ultimately enhance deepfake detection technology and strengthen overall cybersecurity measures that will effectively mitigate exploitation risks and safeguard personal and organizational interests. 

This report will discuss and analyze the risks and challenges associated with smart home devices, focusing on vulnerabilities in commonly used products such as smart speakers, security cameras, thermostats, and lighting systems. As the adoption of smart home security grows globally, it has become clear that many users remain unaware of the associated security risks, leading to data breaches and potential privacy violations. This research evaluates the security features of these devices, the frequency of breaches, and common vulnerabilities. Using a mixed-methods approach—including a user survey, analysis of past cybersecurity incidents, and a detailed review of existing literature—this study assesses the current state of smart home device security. The findings aim to highlight gaps in user awareness, evaluate manufacturers’ protective measures, and provide recommendations for improving cybersecurity practices in smart home environments.