A Framework for Detection and Classification of Attacks on Surveillance Cameras under IoT Networks

• URL: http://arxiv.org/abs/2509.05366v1
• Date: Thu, 04 Sep 2025 05:33:41 GMT
• Title: A Framework for Detection and Classification of Attacks on Surveillance Cameras under IoT Networks
• Authors: Umair Amjid, M. Umar Khan, S. A. Manan Kirmani,
• Abstract summary: The proposed framework will leverage machine learning algorithms to analyze network traffic and detect anomalous behavior.<n>The framework will be trained and evaluated using real-world datasets to learn from past security incidents.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The increasing use of Internet of Things (IoT) devices has led to a rise in security related concerns regarding IoT Networks. The surveillance cameras in IoT networks are vulnerable to security threats such as brute force and zero-day attacks which can lead to unauthorized access by hackers and potential spying on the users activities. Moreover, these cameras can be targeted by Denial of Service (DOS) attacks, which will make it unavailable for the user. The proposed AI based framework will leverage machine learning algorithms to analyze network traffic and detect anomalous behavior, allowing for quick detection and response to potential intrusions. The framework will be trained and evaluated using real-world datasets to learn from past security incidents and improve its ability to detect potential intrusion.

Related papers

• Leveraging Machine Learning for Botnet Attack Detection in Edge-Computing Assisted IoT Networks [0.34530027457862006]
  This paper investigates the application of machine learning techniques to enhance security in Edge-Computing-Assisted IoT environments.<n>It presents a comparative analysis of Random Forest, XGBoost, and LightGBM to address the dynamic and complex nature of botnet threats.<n>The results highlight the potential of machine learning to fortify IoT networks against emerging cybersecurity challenges.
  arXiv  Detail & Related papers  (2025-08-03T01:52:35Z)
• CANDoSA: A Hardware Performance Counter-Based Intrusion Detection System for DoS Attacks on Automotive CAN bus [45.24207460381396]
  This paper presents a novel Intrusion Detection System (IDS) designed for the Controller Area Network (CAN) environment.<n>A RISC-V-based CAN receiver is simulated using the gem5 simulator, processing CAN frame payloads with AES-128 encryption as FreeRTOS tasks.<n>Results indicate that this approach could significantly improve CAN security and address emerging challenges in automotive cybersecurity.
  arXiv  Detail & Related papers  (2025-07-19T20:09:52Z)
• Enabling Security on the Edge: A CHERI Compartmentalized Network Stack [42.78181795494584]
  CHERI provides strong security from the hardware level by enabling fine-grained compartmentalization and memory protection.<n>Our case study examines the trade-offs of isolating applications, TCP/IP libraries, and network drivers on a CheriBSD system deployed on the Arm Morello platform.
  arXiv  Detail & Related papers  (2025-07-07T09:37:59Z)
• Intelligent Detection of Non-Essential IoT Traffic on the Home Gateway [45.70482328441101]
  This work presents ML-IoTrim, a system for detecting and mitigating non-essential IoT traffic by analyzing network behavior at the edge.<n>We test our framework in a consumer smart home setup with IoT devices from five categories, demonstrating that the model can accurately identify and block non-essential traffic.<n>This research advances privacy-aware traffic control in smart homes, paving the way for future developments in IoT device privacy.
  arXiv  Detail & Related papers  (2025-04-22T09:40:05Z)
• Machine Learning-Assisted Intrusion Detection for Enhancing Internet of Things Security [1.2369895513397127]
  Attacks against the Internet of Things (IoT) are rising as devices, applications, and interactions become more networked and integrated. To efficiently secure IoT devices, real-time detection of intrusion systems is critical. This paper investigates the latest research on machine learning-based intrusion detection strategies for IoT security.
  arXiv  Detail & Related papers  (2024-10-01T19:24:34Z)
• I Still See You: Why Existing IoT Traffic Reshaping Fails [14.077052412195263]
  Internet traffic data produced by the Internet of Things (IoT) devices are collected by Internet Service Providers (ISPs) and device manufacturers. On-path adversaries could infer and fingerprint users' sensitive privacy information by analyzing these network traffic traces. There's currently no systematic method to compare and evaluate the comprehensiveness of existing studies.
  arXiv  Detail & Related papers  (2024-06-14T18:11:44Z)
• Classification of cyber attacks on IoT and ubiquitous computing devices [49.1574468325115]
  This paper provides a classification of IoT malware. Major targets and used exploits for attacks are identified and referred to the specific malware. The majority of current IoT attacks continue to be of comparably low effort and level of sophistication and could be mitigated by existing technical measures.
  arXiv  Detail & Related papers  (2023-12-01T16:10:43Z)
• Forensics and security issues in the Internet of Things [6.422895251217666]
  This paper reviews forensic and security issues associated with IoT in different fields.<n>Most IoT devices are vulnerable to attacks due to a lack of standardized security measures.<n>To fulfill the security-conscious needs of consumers, IoT can be used to develop a smart home system.
  arXiv  Detail & Related papers  (2023-09-06T04:41:48Z)
• Intrusion Detection using Network Traffic Profiling and Machine Learning for IoT [2.309914459672557]
  A single compromised device can have an impact on the whole network and lead to major security and physical damages. This paper explores the potential of using network profiling and machine learning to secure IoT against cyber-attacks.
  arXiv  Detail & Related papers  (2021-09-06T15:30:10Z)
• TANTRA: Timing-Based Adversarial Network Traffic Reshaping Attack [46.79557381882643]
  We present TANTRA, a novel end-to-end Timing-based Adversarial Network Traffic Reshaping Attack. Our evasion attack utilizes a long short-term memory (LSTM) deep neural network (DNN) which is trained to learn the time differences between the target network's benign packets. TANTRA achieves an average success rate of 99.99% in network intrusion detection system evasion.
  arXiv  Detail & Related papers  (2021-03-10T19:03:38Z)
• Measurement-driven Security Analysis of Imperceptible Impersonation Attacks [54.727945432381716]
  We study the exploitability of Deep Neural Network-based Face Recognition systems. We show that factors such as skin color, gender, and age, impact the ability to carry out an attack on a specific target victim. We also study the feasibility of constructing universal attacks that are robust to different poses or views of the attacker's face.
  arXiv  Detail & Related papers  (2020-08-26T19:27:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.