Summary of Secure Hierarchical Federated Learning in Vehicular Networks Using Dynamic Client Selection and Anomaly Detection, by M. Saeid Haghighifard et al.
Secure Hierarchical Federated Learning in Vehicular Networks Using Dynamic Client Selection and Anomaly Detection
by M. Saeid HaghighiFard, Sinem Coleri
First submitted to arxiv on: 25 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Hierarchical Federated Learning (HFL) faces a significant challenge due to adversarial or unreliable vehicles in vehicular networks, compromising model integrity. To address this, we introduce a novel framework integrating dynamic vehicle selection and robust anomaly detection mechanisms to optimize participant selection and mitigate risks from malicious contributions. Our approach involves comprehensive vehicle reliability assessment considering historical accuracy, contribution frequency, and anomaly records. We utilize an anomaly detection algorithm analyzing cosine similarity of local or model parameters during the FL process to identify anomalous behavior. Anomaly records are registered and combined with past performance for accuracy and contribution frequency to identify suitable vehicles for each learning round. Dynamic client selection and anomaly detection algorithms are deployed at different levels, including cluster heads (CHs), cluster members (CMs), and Evolving Packet Core (EPC) to detect and filter out spurious updates. Our proposed algorithm demonstrates remarkable resilience even under intense attack conditions through simulation-based performance evaluation, achieving convergence times 63% as effective as scenarios without attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine a big network of connected cars that learn from each other’s experiences. But what if some of these cars are trying to trick the system? This can happen when vehicles in a vehicular network try to provide fake updates to compromise the model. To solve this problem, we developed a new way to select which vehicles should be part of the learning process and detect any suspicious behavior. Our approach looks at each vehicle’s past performance, how often they contribute, and if they’re behaving strangely. We then use these records to pick the most reliable vehicles for each learning round. Our method shows that it can effectively deal with malicious attacks and still achieve good results. In fact, our algorithm is 63% as effective as one without any attacks. |
Keywords
» Artificial intelligence » Anomaly detection » Cosine similarity » Federated learning
