Directed Acyclic Graphs (DAGs) — aka the Blockchain Killers!

Popular Implementations: Iota, Hashgraph, Raiblocks/Nano

 

Pros: Network Scalability; low cost

Cons: Depends on implementation

 

DAGs are hotter than Vitalik’s Tinder profile right now. DAGs are a form of consensus that doesn’t use the blockchain data structure and handles transactions mostly asynchronously. The big pro is theoretically infinite transactions per second, but DAGs have strengths and weaknesses like any other consensus.

Tangle: Tangle is the DAG consensus algorithm used by Iota. In order to send an Iota transaction, you need to validate two previous transactions you’re received. The two-for-one, pay-it-forward consensus strengthens the validity of transactions the more transactions are added to the Tangle. Because the consensus is established by the transactions, theoretically, if someone can generate 1/3 of the transactions they could convince the rest of the network their invalid transactions are valid. Until there’s enough transaction volume that creating 1/3rd of the volume becomes unfeasible, Iota is sort-of “double-checking” all of the network’s transactions on a centralized node called “The Coordinator”. Iota says The Coordinator works like training wheels for the system, and will be removed once the Tangle is big enough.

 

Hashgraph: Hashgraph is a gossip-protocol consensus developed by Leemon Baird. Nodes share their known transactions with other nodes at random so eventually all the transactions are gossiped around to all of the nodes. Hashgraph is really fast (250,000+ transactions per second) but isn’t resistant to Sybil attacks. So Hashgraph is a great option for private networks, but you’re not going to see it implemented in a public network like Ethereum or Dispatch any time soon.

Block-lattice: Nano (formerly Raiblocks) runs with a twist on the blockchain called a Block-lattice. The Block-lattice is a structure where every user (address) gets their own chain that only they can write to, and everyone holds a copy of all of the chains. Every transaction is broken down into both a send block on the sender’s chain and a receive block on the receiving party’s chain. The Block-lattice seems almost too simple to work, but it’s already out there running in the wild. The unique structure does leave the Block-lattice open to some unique attack vectors like the Penny-spend attack, where attackers inflate the number of chains node must keep track of by sending negligible amounts to a wide array of empty wallets.

SPECTRE: Serialization of Proof-of-work Events: Confirming Transactions via
Recursive Elections, better known as SPECTRE, is a proposed Bitcoin scaling solution that utilizes a combination of PoW and DAGs to reach scalable consensus. In SPECTRE, the blocks are mined pointing to multiple parents, not just one, so the network could potentially handle multiple blocks per second. Mining a block pointing to some parent blocks supports those blocks validity. Compared to PoW’s “longest chain wins”, SPECTRE uses something like “blocks with the most childen win.” SPECTRE hasn’t been battle-tested in the wild yet, and new attack vectors are likely to emerge, but it feels like a very clever potential way to fix Bitcoin.