Redactable blockchain presents a solution for fraudulent transaction modification and storage overload by allowing limited data manipulation using Chameleon Hash Functions (CHF). However, CHF-based redactable blockchain encounters significant security challenges like misuse of edit rights, node desynchronization, higher transaction verification, and redaction latency. To solve these challenges, we propose SERB, a secure and efficient redactable blockchain protocol. SERB utilizes a Node Selection, Redactable Consensus, and novel Parameterized Chameleon Hash Function (pCHF) for proper use of edit rights and node synchronization with minimization of transaction verification and redaction latency. The security analysis shows that SERB is secured against tampering attacks, collusion attacks, and forged attacks. The performance analysis indicates that the SERB reduces transaction verification latency by 20% and minimizes redaction latency, such as transaction modification by 25 % and block deletion by$\mathbf{5 0 \%}$compared to state-of-the-art approaches.

Vision-based motion planning is a crucial task in Autonomous Driving (AD). Recent advancements in urban AD show that integrating Imitation Learning (IL) with Deep Reinforcement Learning (DRL) improves decision-making to be more like humans. However, IL methods depend on expert demonstrations to learn the optimal policy. The main drawback of this approach is the assumption that expert demonstrations are always optimal, which is not always true in real-world settings. This creates challenges in adapting to diverse weather conditions and dynamic traffic scenarios, often resulting in higher collision rates and increased risks to pedestrian safety. To address these challenges, we propose a Diffusion-Guided Deep Reinforcement Learning (DGDRL) framework that integrates a diffusion model with a Soft Actor-Critic DRL method to effectively mitigate environmental uncertainties and enable self-learning beyond the training maps for new tasks. This framework follows a novel modified partially observable Markov decision process (mPOMDP) to choose optimal action from original and diffusion-generated observations, ensuring that the policy behavior remains consistent with the current action. We use the CARLA NoCrash benchmark to train and evaluate the proposed framework. The method is validated in diverse urban environments (e.g., empty, regular, and dense) across multiple towns. Additionally, we compare our model against state-of-the-art techniques to ensure robustness and generalizability to new environments. The project page and code are available at the link https://autovisionproject.github.io/project/.

The Internet of Vehicles (IoV) enables vehicles and Road-Side-Unit to communicate and exchange data, promising to improve transportation safety, efficiency, and convenience. However, to realize the full potential of IoV, secure and fast traffic accident information (TAI) communication among IoV nodes are essential. The Practical Byzantine Fault Tolerance (PBFT)-based blockchain for IoV secures TAI; it is prone to high message overhead and transaction latency, which causes TAI transmission between IoV nodes to be delayed. This paper proposes a new consensus algorithm, named HN-mPBFT (Healthy Node based Modified PBFT), specifically designed for IoV. The HN-mPBFT consensus method reduces message overhead and transaction delay by reducing PBFT consensus phases while achieving consensus among healthy nodes. According to security analysis, HN-mPBFT is secure from Sybil and DDoS attacks. Performance analysis shows that HN-mPBFT reduces transaction latency by 50%.