Agentic AI

LLM‑driven systems that autonomously decompose tasks, call tools, and coordinate with other agents to reach goals.

Adversarial Example

Input crafted to fool a model into misclassification or unsafe behavior without obvious changes to humans.

Attention Mechanism

Technique that lets models weight different parts of input sequences, central to transformers and modern LLMs.

Autoencoder

Neural network trained to compress and reconstruct inputs, useful for denoising, anomaly detection, and latent features.

Auto‑compound

Mechanism that periodically claims and reinvests rewards back into a position to increase APY.

Atomic Swap

Cross‑chain trade that either completes for both parties or reverts for both, often using HTLCs.

Attestation

Verifiable statement about an identity, event, or state. Used in staking, oracles, and decentralized identity.

Asymmetric Encryption

Cryptography using public and private keys, enabling signatures and secure key exchange over open networks.

ASIC Miner

Specialized hardware optimized to compute a specific proof‑of‑work algorithm at very high efficiency.