Open
Conversation
FAISS (Facebook AI Similarity Search) is a C++ library for efficient similarity search and clustering of dense vectors, maintained by Meta with ~40K stars. It is widely deployed in production ML systems as a transitive dependency in vector databases, RAG pipelines, and recommendation engines. This adds a libFuzzer harness targeting FAISS index deserialization (read_index, read_index_binary, read_ProductQuantizer) plus runtime exercise of search, range_search, reconstruct, assign, compute_residual, and sa_decode on successfully-loaded indices. Sanitizers: ASan + UBSan. Engines: libFuzzer, AFL, honggfuzz.
|
Sheri98 is integrating a new project: |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add libFuzzer harness for FAISS, Meta's similarity search library (~40K stars)
FAISS is a transitive dependency in production vector databases, RAG pipelines, and recommendation engines
Harness targets index deserialization (
read_index,read_index_binary,read_ProductQuantizer) plus runtime exercise ofsearch,range_search,reconstruct,assign,compute_residual, andsa_decodeon successfully-loaded indicesIncludes 15-seed corpus covering Flat, HNSW, IVFFlat, IVFPQ, PQ, ScalarQuantizer, LSH, IDMap, PreTransform, and Binary index families
Includes dictionary with index magic bytes and format tokens
Sanitizers: ASan + UBSan
Engines: libFuzzer, AFL, honggfuzz
Test plan
CLA check passes
Container build succeeds for all sanitizer/engine combinations
Harness achieves >10% function coverage on seed corpus replay