Detecting vulnerabilities in smart contracts is critical due to their immutability and the billions of dollars they secure. Industrial tools like Slither rely on hardcoded rules, often missing rare bugs or producing excessive false positives. Recent work with large language models (LLMs) such as GPT-5 has been applied to this task, but these models favor precision while failing to recall many true issues, especially in multi-label settings.

We first fine-tune a 220M CodeT5+ model on over 67,000 real-world Ethereum contracts to establish a per-class detectability baseline, revealing which SWC vulnerabilities are intrinsically easier or harder to detect. We then study scaling effects, showing that the 770M variant improves majority-class precision but loses rare-class sensitivity.

To reconcile this trade-off, we propose BreachT5, a soft-voting ensemble of both scales with tuned thresholds to balance recall and precision. BreachT5 achieves 0.556 Macro-F1 and 0.612 Micro-F1, outperforming standalone models, Slither, and GPT-5 on multi-label vulnerability detection in smart contract security.

Despite recent advances in robotic technology, sewer pipe inspection is still limited to conventional approaches that use cable-tethered robots. Such commercially available tethered robots lack autonomy, and their operation must be manually controlled via their tethered cables. Consequently, they can only travel to a certain distance in pipe, cannot access small-diameter pipes, and their deployment incurs high costs for highly skilled operators. In this paper, we introduce a miniaturised mobile robot for pipe inspection. We present an autonomous control strategy for this robot that is effective, stable, and requires only low-computational resources. The robots used here can access pipes as small as 75 mm in diameter. Due to their small size, low carrying capacity, and limited battery supply, our robots can only carry simple sensors, a small processor, and miniature wheel-legs for locomotion. Yet, our control method is able to compensate for these limitations. We demonstrate fully autonomous robot mobility in a sewer pipe network, without any visual aid or power-hungry image processing. The control algorithm allows the robot to correctly recognise each local network configuration, and to make appropriate decisions accordingly. The control strategy was tested using the physical micro robot in a laboratory pipe network. In both simulation and experiment, the robot autonomously and exhaustively explored an unknown pipe network without missing any pipe section while avoiding obstacles. This is a significant advance towards fully autonomous inspection robot systems for sewer pipe networks.

Fraudulent behavior within online marketplaces is a prominent but unsolved problem. Most marketplace operators try to mitigate this behavior by serving as the central authority. This approach requires user data collection and is not privacy-friendly. In an attempt to build a foundation for solving the fraud concerns and privacy issues, this paper elaborates on the design and implementation of a simple marketplace system using peer-to-peer (P2P) technology in combination with a Self-Sovereign Identity (SSI) solution. The P2P network ensures no single points of control, reduces risks of a big data breach and simply costs less to operate. The SSI solution makes sure that users cannot create multiple accounts to whitewash their dishonest behavior. Ensuring every user has only one identity makes the platform Sybil-resistant. In contrast to other identity verification systems used in marketplaces, such as Facebook Login, SSI aims to put the user in control and to not collect personal data. Users know what data are asked and give explicit consent for each request. This user-centric approach makes them privacy-friendly. Reaching Sybil resistance without having a central authority in a marketplace has not been done before. In the future a reputation system can be built on top of the Sybil-resistant P2P system, ensuring users’ behavior can not be whitewashed. Several methods are used during the design and the implementation process. They include the Scrum framework, MoSCoW prioritization and Class-Responsibility-Collaboration cards. Git was used for version control while code quality was kept high through a custom CI setup. Additionaly, every merge request required at least two approvals to ensure thorough code review. This resulted in an application that is both Sybil-resistant and privacy-friendly