HiFuzz

Tool

First seen 7/10/2026

Last seen 7/10/2026

Evidence 13 chunks

NEIGHBORHOOD

No graph connections found for this entity yet. It may appear in future ingestion runs.

explore full graph →

RELATIONSHIPS

34 connections

differential testing uses → 85% 2e

HiFuzz uses differential testing against Spike as the reference model to detect bugs.

Hierarchical Reinforcement Learning implements → 100% 2e

HiFuzz implements a hierarchical reinforcement learning framework with a two-level agent hierarchy.

Hardware fuzzing implements → 100% 2e

HiFuzz is a hardware fuzzing tool targeting CPU verification.

Constructive Test Generation implements → 95% 2e

HiFuzz uses constructive generation to assemble programs instruction by instruction rather than mutating seeds.

Coverage-guided Fuzzing implements → 90% 2e

HiFuzz uses coverage feedback to guide the reinforcement learning agents toward better test generation.

Program Agent uses → 100% 2e

HiFuzz uses a Program Agent as the high-level planner for global test program structure.

Basic Block Agent uses → 100% 2e

HiFuzz uses a Basic Block Agent as the low-level executor for instruction filling.

Semantic-Aware Basic Block Encoder uses → 100% 2e

HiFuzz integrates a Semantic-Aware Basic Block Encoder to provide intrinsic novelty feedback.

Adaptive Coverage Reward Mechanism uses → 100% 2e

HiFuzz uses an Adaptive Coverage Reward Mechanism to balance module-level exploration.

Intrinsic Novelty Reward uses → 100% 2e

HiFuzz uses an intrinsic novelty reward derived from the BB encoder embeddings to provide dense feedback.

line coverage evaluates → 90% 2e

HiFuzz measures line coverage on Rocket using Verilator.

toggle coverage evaluates → 90% 2e

HiFuzz measures toggle coverage on Rocket using Verilator.

Program Agent ← part of 100% 2e

The Program Agent is a component of the HiFuzz dual-agent architecture.

Basic Block Agent ← part of 100% 2e

The Basic Block Agent is a component of the HiFuzz dual-agent architecture.

Semantic-Aware Basic Block Encoder ← part of 100% 2e

The Semantic-Aware BB Encoder is a feedback component of HiFuzz.

Adaptive Coverage Reward Mechanism ← part of 100% 2e

The ACRM is a feedback component of HiFuzz for balanced module-level coverage.

RISC-V uses → 100% 2e

HiFuzz generates RISC-V programs to fuzz RISC-V processor cores.

spike uses → 100% 2e

HiFuzz uses Spike as the reference model for differential testing on RISC-V cores.

ISA Pre-Simulation uses → 90% 2e

HiFuzz uses an ISA pre-simulation step to validate generated programs before RTL simulation.

Rocket Core evaluates → 100% 2e

HiFuzz is evaluated on the Rocket Core as one of three RISC-V targets.

BOOM core evaluates → 100% 2e

HiFuzz is evaluated on the BOOM Core as one of three RISC-V targets.

CVA6 evaluates → 100% 2e

HiFuzz is evaluated on CVA6 as one of three RISC-V targets.

DiFuzzRTL ← compares with 100% 2e

HiFuzz is compared against DifuzzRTL as a baseline fuzzer.

ProcessorFuzz compares with → 100% 2e

HiFuzz is compared against ProcessorFuzz as a baseline fuzzer.

Cascade ← compares with 100% 2e

HiFuzz is compared against Cascade as a baseline fuzzer, outperforming it by 48.9% on control register coverage.

Control Register Coverage evaluates → 100% 2e

HiFuzz is evaluated using control register coverage as its primary metric on Rocket.

Mux Coverage evaluates → 90% 2e

HiFuzz reports MUX coverage on Rocket and BOOM cores.

Hierarchical Configuration uses → 95% 1e

HiFuzz uses a hierarchical configuration mechanism splitting global structure from per-BB content.

Verilator uses → 100% 1e

HiFuzz is implemented on top of Verilator for RTL simulation.

Hierarchical Configuration ← part of 90% 1e

Hierarchical Configuration is a core mechanism of HiFuzz for splitting global and local program decisions.

CocoTB uses → 100% 1e

HiFuzz is implemented on top of Cocotb for hardware simulation interfacing.

Encarsia evaluates → 90% 1e

HiFuzz is evaluated using the Encarsia benchmark for bug detection.

GenHuzz ← compares with 90% 1e

HiFuzz is structurally compared with GenHuzz as a related generative fuzzer.

HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing ← introduces 100% 1e

The paper introduces HiFuzz as a novel hierarchical reinforcement learning framework for CPU fuzzing.