GoldenFuzz
ToolFirst seen 6/14/2026
Last seen 8/22/2026
Evidence 29 chunks
NEIGHBORHOOD
No graph connections found for this entity yet. It may appear in future ingestion runs.
explore full graph →RELATIONSHIPS
50 connectionsGoldenFuzz leverages a Golden Reference Model as a digital twin of the DUT.
GoldenFuzz targets the Device Under Test for vulnerability discovery after refining test cases on the GRM.
GoldenFuzz implements hardware fuzzing for processor RTL verification and vulnerability discovery.
GoldenFuzz was evaluated on CVA6, discovering five new vulnerabilities.
GoldenFuzz uses the Golden Reference Model as a digital twin of the Device Under Test.
The paper introduces the GoldenFuzz tool for hardware fuzzing.
GoldenFuzz was evaluated on the BOOM processor design, achieving superior coverage results.
GoldenFuzz implements coverage-guided fuzzing in its second stage for DUT-level exploration.
GoldenFuzz was evaluated on and tested against the RocketChip processor design.
GoldenFuzz is described as a novel two-stage hardware fuzzing framework.
GoldenFuzz constructs test programs from instruction blocks generated and scored by the policy model.
GoldenFuzz is compared against ChatFuzz as a baseline hardware fuzzer.
GoldenFuzz explicitly pairs winning and losing test cases as preference pairs to refine its fuzzing policy.
GoldenFuzz uses a fast, ISA-compliant Golden Reference Model for test generation.
GoldenFuzz is compared against Cascade as a prior state-of-the-art hardware fuzzer.
GoldenFuzz is compared against DifuzzRTL, achieving 3.33× speedup over it.
GoldenFuzz was evaluated on the commercial BA51-H processor core, finding two confidential bugs.
GoldenFuzz uses Direct Preference Optimization (DPO) concepts to refine its fuzzing policy.
GoldenFuzz uses Synopsys VCS as an RTL simulation backend for DUT-level fuzzing.
GoldenFuzz is compared against TheHuzz as a baseline hardware fuzzer.
GoldenFuzz constructs test cases by concatenating carefully chosen instruction blocks.
GoldenFuzz partially decouples test case refinement from coverage and vulnerability exploration.
GoldenFuzz uses a GPT-2-based LLM to generate instruction blocks for its first fuzzing stage.
GoldenFuzz employs differential testing by comparing DUT and GRM execution traces.
GoldenFuzz introduces a block-wise test case generation scheme.
GoldenFuzz employs intra-test case scoring to incentivize newly uncovered coverage within a single test case.
GoldenFuzz employs inter-test case scoring to deduct coverage already found by other tests.
GoldenFuzz's instruction generation must internalize intra-instruction semantics.
GoldenFuzz's instruction generation must internalize inter-instruction semantics.
GoldenFuzz implements a customized GPT model for RISC-V assembly instruction generation.
GoldenFuzz employs Spike as the GRM during the profiling stage.
GoldenFuzz measures FSM coverage as part of its evaluation.
GoldenFuzz measures condition coverage as part of its evaluation.
GoldenFuzz measures line coverage as part of its evaluation.
GoldenFuzz is pre-trained on a corpus of RISC-V assembly instructions.
GoldenFuzz identifies discrepancies between DUT and GRM traces as potential vulnerabilities.
GoldenFuzz refines test case validity based on ISA during GRM fuzzing.
GoldenFuzz learns to generate test cases that involve privilege mode transitions.
GoldenFuzz learns PMP configurations as part of its semantic understanding.
GoldenFuzz discovers endianness vulnerabilities in CVA6.
GoldenFuzz accelerates deep architectural exploration on the DUT.
GoldenFuzz employs a feedback-driven mechanism leveraging insights from high- and low-coverage samples.
GoldenFuzz introduces and implements a two-stage pipeline separating policy refinement from coverage-guided DUT fuzzing.
GoldenFuzz uses SimPO to update the policy on preference pairs to maximize ISA-valid instruction generation and coverage.
GoldenFuzz drives both RTL DUT and GRM in lockstep, comparing outputs after each instruction to detect bugs.
GoldenFuzz uses ModelSim as an RTL simulation backend for DUT-level fuzzing.
GoldenFuzz measures and reports condition coverage improvements over prior tools.
GoldenFuzz measures FSM coverage and matches state-of-the-art on RocketChip.
The Wu et al. 2025 paper introduces GoldenFuzz as a novel hardware fuzzing framework.
Nikhilesh Singh is listed as an author affiliated with TU Darmstadt.