Related papers: Fortytwo: Swarm Inference with Peer-Ranked Consens…
We present Intercloud, a decentralised economic network in which streams of private data are secured by Watcher swarms that observe only cryptographic hashes, never plaintext. Intercloud requires no global consensus beyond a single shared…
As artificial intelligence (AI) continues to permeate various domains, concerns surrounding trust and transparency in AI-driven inference and training processes have emerged, particularly with respect to potential biases and traceability…
The Internet of Vehicles (IoV) is an application of the Internet of things (IoT). It faces two main security problems: (1) the central server of the IoV may not be powerful enough to support the centralized authentication of the rapidly…
The popularity of IoT smart things is rising, due to the automation they provide and its effects on productivity. However, it has been proven that IoT devices are vulnerable to both well established and new IoT-specific attack vectors. In…
Large-scale content analysis is increasingly limited by the absence of observable ground truth or gold-standard labels, as creating such benchmarks through extensive human coding becomes impractical for massive datasets due to high time,…
Recent advances in probabilistic modelling have led to a large number of simulation-based inference algorithms which do not require numerical evaluation of likelihoods. However, a public benchmark with appropriate performance metrics for…
Sybil attacks are a fundamental threat to the security of distributed systems. Recently, there has been a growing interest in leveraging social networks to mitigate Sybil attacks. However, the existing approaches suffer from one or more…
We present a set of metrics intended to supplement designer intuitions when designing swarm-robotic systems, increase accuracy in extrapolating swarm behavior from algorithmic descriptions and small test experiments, and lead to faster and…
The state-of-the-art HotStuff operates an efficient pipeline in which a stable leader drives decisions with linear communication and two round-trips of message. However, the unifying proposing-voting pattern is not sufficient to improve the…
The CTI (Cyber Threat Intelligence) sharing and exchange is an effective method to improve the responsiveness of the protection party. Blockchain technology enables sharing collaboration consortium to conduct a trusted CTI sharing and…
The modeling of emergent swarm intelligence constitutes a major challenge and it has been tackled in a number of different ways. However, existing approaches fail to capture the nature of swarm intelligence and they are either too abstract…
Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with…
The widespread adoption of large-scale machine learning models in recent years highlights the need for distributed computing for efficiency and scalability. This work introduces a novel distributed machine learning paradigm --…
Decentralized large language model inference networks require lightweight mechanisms to reward high quality outputs under heterogeneous latency and cost. Proof of Quality provides scalable verification by sampling evaluator nodes that score…
Swarms have distributed control and so are assumed to inherently have superior robustness, scalability and adaptability compared to centralised multi-agent systems. However, these features have generally only been defined qualitatively and…
When generating insights from human groups, conversational deliberation is a key method for exploring issues, surfacing ideas, debating options, and converging on solutions. Unfortunately, real-time conversations are difficult to scale,…
Intuitively, an ideal collaborative filtering (CF) model should learn from users' full rankings over all items to make optimal top-K recommendations. Due to the absence of such full rankings in practice, most CF models rely on pairwise loss…
A family of leaderless, decentralized consensus protocols, called Snow consensus was introduced in a recent whitepaper by Yin et al. These protocols address limitations of existing consensus methods, such as those using proof-of-work or…
Despite being among the most common psychological disorders, anxiety-related conditions are still primarily identified through subjective assessments, such as clinical interviews and self-evaluation questionnaires. These conventional…
Motivated by undetectable risks in generative AI, we study a general robust aggregation problem: how to aggregate several probability distributions to boost safety. We present consensus sampling, a black-box algorithm that, given k…