SPETViD
International Workshop on Security and Privacy Enhancing Technologies for Visual Data
-
Aug 02, 2024
-
SR04
-
13:30 — 15:00
Workshop Chairs
- → Mamoona Asghar
- → Amna Shifa
- → Nadia Kanwal
Accepted Paper
Chain Links on Wheels: A Security Scheme for IoV Connectivity through Blockchain Integration
Ibtisam Ehsan
(University of Chinese Academy of Sciences, Beijing, China, China), Muhammad Irfan Khalid
(University of Sialkot, Pakistan), Mansoor Ahmed
(ADAPT Centre, Innovation Value Institute, Maynooth University Maynooth, Ireland, Ireland), Markus Helfert
(ADAPT Centre, Innovation Value Institute, Maynooth University Maynooth, Ireland, Ireland)
Full Paper
Vehicles are taking a major step towards connected transportation with advanced applications and robust security frameworks. Despite growth in networking potential in the automotive industry, security and privacy vulnerabilities continue to plague the industry. Internet of Vehicles, one of the subsets of cyber-physical systems, can utilize smart sensors to collect and synthesize data from connected vehicles. This technological development contributes to seamless information exchange between drivers, manufacturers, insurers, and service providers. For effective IoV systems, optimizing spectrum usage, allocating quality channels judiciously, and using infrastructure efficiently to maintain connectivity under changing traffic conditions are essential. However, security and privacy remain the main concerns of these communication networks. With the advent of blockchain technology, the world of cryptocurrency transactions can benefit from a secure communication framework that can alleviate these concerns. We propose integrating blockchain technology into IoV infrastructure in order to facilitate secure, reliable, and trust-enhancing communication between vehicles. We utilize a distributed access control system in order to ensure scalable and strategic decision-making processes. Our results and evaluation show that the use of distributed storage across cloud platforms helps enhance data security, enabling vehicles to exchange information safely.
Workshop SPETViD
Workshop SPETViD
GDPR-compliant Video Search and Retrieval System for Surveillance Data
Amna Shifa
(University of Galway School of Computer Science , Ireland), Rónán Kennedy
(University of Galway School of Law, Ireland),
(University of Galway School of Computer Science, Ireland)
Full Paper
The widespread deployment of surveillance cameras, responding to the increasing demand for scene investigation, video forensics, and analytics in urban environments, necessitates the storage and accurate retrieval of required video shots for post-verification. Conventional CCTV systems lack intelligent data storage, resulting in substantial volumes of data. This massive volume of video data (big data) poses a challenge in searching and retrieving needed information for video content analysis (VCA). Moreover, surveillance videos often contain sensitive Personally Identifiable Information (PII) about individuals, raising concerns about privacy and data protection. Data protection is vital for ethics and a fundamental human right. European regulatory authorities have enforced the General Data Protection Regulation (GDPR) to safeguard individuals’ privacy rights and mitigate security threats. GDPR emphasizes data minimisation by collecting the minimum amount of personal data needed to deliver an individual service element. However, there is no mechanism to preserve the privacy of stored videos along with minimisation. Therefore, several ethical issues arise, limiting the use of automated surveillance systems. This work proposes a multi-layered security framework by integrating summarisation and attribute-based searchable encryption to provide optimal secure storage and intelligently filter out desired video clips from the encrypted videos by employing a text-to-video retrieval technique, making it a resource-efficient and GDPR-compliant secure evidence management system.
Workshop SPETViD
Workshop SPETViD
Detail SPETViD 02/05
International Workshop on Security and Privacy Enhancing Technologies for Visual Data to be held in conjunction with the 19th International Conference on Availability, Reliability and Security
Visual data, such as images, videos, and 3D models, have a significant impact on our daily lives. It is increasingly captured for purposes such as safety, tracking movements, monitoring activities, diagnosing diseases, and behaviour prediction in smart systems (homes, healthcare, transportation, etc.). From casual snapshots to complex satellite images, visual information can reveal personal or sensitive information, including facial recognition, license plates, address/locations of landmarks, disease type, and sensitive documents, which can be exploited by malicious actors. Furthermore, the increasing sophistication of Artificial Intelligence (AI) based recognition technologies raises privacy concerns. Conventional automated intelligent systems do not promise privacy or personal data security. Visual data protection requires a multifaceted approach involving technological solutions, strong legal frameworks, ethical practices, transparency, accountability, and individual awareness. Therefore, privacy protection, along with secured data retention and delivery is the biggest challenge in the design and deployment of intelligent and reliable visual analytics systems.
SPETVid workshop aims to connect visual data security and privacy, exploring advanced cryptographic methods, visual obfuscation, PETs, anonymization, pseudonymization, privacy-preserving analysis, machine learning, blockchain, data minimization, summarization, synthetic/generative data, and emerging technologies that will shape visual data privacy and security.
SPETViD workshop bridges academia, practitioners, law enforcement, and industry for secure and privacy-preserving visual data research. It seeks theoretical, conceptual, and experimental contributions to visual data security and privacy, enabling participants to exchange and discuss the latest findings and solutions.
SPETVid workshop aims to connect visual data security and privacy, exploring advanced cryptographic methods, visual obfuscation, PETs, anonymization, pseudonymization, privacy-preserving analysis, machine learning, blockchain, data minimization, summarization, synthetic/generative data, and emerging technologies that will shape visual data privacy and security.
SPETViD workshop bridges academia, practitioners, law enforcement, and industry for secure and privacy-preserving visual data research. It seeks theoretical, conceptual, and experimental contributions to visual data security and privacy, enabling participants to exchange and discuss the latest findings and solutions.
Topics of interest include, but are not limited to 03/05
- Authentication of visual data (authentication algorithms, PKI and hashing)
- Blockchain technology for Visual Chain-of-Evidence / Tamper-proof visual data
- Computer vision for visual privacy
- Cryptography and steganography techniques for visual data
- Emerging threats and vulnerabilities on visual data (Deepfakes, Zero-day attacks on visual recognition systems, and data poisoning techniques)
- Ethical processing of Visual data
- Federated and Distributed Analytics
- Generative / Synthetic Data Generation Techniques / Generative AI Media
- Global and European Policy and Regulatory Frameworks (e.g., GDPR)
- Image processing and Machine Learning for tampering detection techniques
- Image processing for privacy protection
- Implications of GDPR on visual information
- Laws affecting visual surveillance in public and private places
- Machine learning in distributed imaginary systems
- Object detection for security applications
- Privacy-preserved tracking and activity recognition
- Privacy-enhancing visual data management
- Privacy-preserving AI and Machine Learning (including Explainable AI (XAI))
- Privacy-preserving technologies for visual data
- Pseudonymization and anonymization Techniques
- Safeguarding visual data With Differential Privacy
- Secure analysis and retrieval of visual data
- Secure Multimedia Internet of Things (MIoT)
- Secure visual data pipelines and storage techniques
- Secure and Verifiable Computation on Encrypted Data
- Standardization and Interoperability
- Summarization, data minimization, and annotation for visual data
- Threat modelling for Visual Data
- Video redaction/obfuscation Techniques
- Visual data enchantment (manipulation/tempering/video quality) techniques
Workshop Chairs 04/05
Workshop Chairs
Program Committee
Asra Aslam
|
University of Leeds, UK
Gazi Erkan Bostanci
|
Ankara University, Turkey
Ihsan Ullah
|
University of Galway, Ireland
Martin Fleury
|
University of Essex, UK
Malika Bendechache
|
University of Galway, Ireland
Muhammad Babar Imtiaz
|
Technological University of the Shannon, Ireland
Muhammad Samar Ansari
|
University of Chester, UK
Rónán Kennedy
|
University of Galway, Ireland
Saeed Alsamhi
|
Insight, Data Science Institute, Ireland
Shoaib Ehsan
|
University of Southampton, UK
Zafar Shahid
|
Meta, US
Yuansong Qiao
|
Technological University of the Shannon, Ireland
Submission 05/05
Submission Guidelines
The submission guidelines valid for the workshop are the same as for the ARES conference.
Important Dates
Submission Deadline
May 15, 2024
Author Notification
May 27, 2024
Proceedings Version
Jun 18, 2024
Conference
Jul 30
—
Aug 02, 2024