arXiv subjects

Vasudev Vikram

Publications and source records attributed to Vasudev Vikram.

5 recordsLinked to original sources

arXiv2026

Fuzzing with Agents? Generators Are All You Need

Modern generator-based fuzzing techniques combine lightweight input generators with coverage-guided mutation as a method of exploring deep execution paths in a target program. A complimentary approach in prior research focuses on creating highly customized, domain-specific generators that encode structural and semantic logic sufficient enough to reach deep program states; the challenge comes from the overhead of writing and testing these complex generators. We investigate whether AI coding agents can automatically synthesize such target-specific generators, and whether the resulting generators are strong enough to obviate the need for coverage guidance and mutation entirely. Our approach, Gentoo, is comprised of an LLM coding agent (provided terminal access and source code of the fuzz target and its library) instructed to iteratively synthesize and refine an input generator, and optionally provided fine-grained predicate-level coverage feedback. We evaluate three configurations of Gentoo against human-written generators on fuzz targets for 7 real-world Java libraries. Our findings show that agent-synthesized generators achieve statistically significantly higher branch coverage than human-written baseline generators on 4 of 7 benchmarks. Critically, the use of coverage guidance and mutation strategies is not statistically significantly beneficial for agent-synthesized generators, but is significant for all human-written generators, suggesting that structural and semantic logic encoded in the agent generators makes coverage guidance largely unnecessary.

cs.SE↗

arXiv2025

On the Freshness of Pinned Dependencies in Maven

Library dependencies in software ecosystems play a crucial role in the development of software. As newer releases of these libraries are published, developers may opt to pin their dependencies to a particular version. While pinning may have benefits in ensuring reproducible builds and avoiding breaking changes, it bears larger risks in using outdated dependencies that may contain bugs and security vulnerabilities. To understand the frequency and consequences of dependency pinning, we first define the concepts of stale and fresh pins, which are distinguished based on how outdated the dependency is relative to the release date of the project. We conduct an empirical study to show that over 60% of consumers of popular Maven libraries contain stale pins to their dependencies, with some outdated versions over a year old. These pinned versions often miss out on security fixes; we find that 10% of all dependency upgrades in our dataset to the latest minor or patch version would reduce security vulnerabilities. We prototype an approach called Pin-Freshener that can encourage developers to freshen their pins by leveraging the insight that crowdsourced tests of peer projects can provide additional signal for the safety of an upgrade. Running Pin-Freshener on dependency upgrades shows that just 1-5 additional test suites can provide 35-100% more coverage of a dependency, compared to that of a single consumer test suite. Our evaluation on real-world pins to the top 500 popular libraries in Maven shows that Pin-Freshener can provide an additional signal of at least 5 passing crowdsourced test suites to over 3,000 consumers to safely perform an upgrade that reduces security vulnerabilities. Pin-Freshener can provide practical confidence to developers by offering additional signal beyond their own test suites, representing an improvement over current practices.

cs.SE↗

arXiv2025

Fray: An Efficient General-Purpose Concurrency Testing Platform for the JVM (Extended Version)

Concurrency bugs are hard to discover and reproduce. Prior work has developed sophisticated algorithms to search for concurrency bugs, such as partial order sampling (POS); however, fundamental limitations with existing platforms for concurrency control hinder effective testing of real-world software. We observe that the design space for concurrency control on managed code involves complex trade-offs between expressibility, applicability, and maintainability on the one hand, and bug-finding efficiency on the other hand. This paper presents Fray, a platform for performing push-button concurrency testing of data-race-free JVM programs. The key insight behind Fray is that effective controlled concurrency testing requires orchestrating thread interleavings without replacing existing concurrency primitives, while encoding their semantics for faithfully expressing the set of all possible program behaviors. Fray incorporates a novel concurrency control mechanism called shadow locking, designed to make controlled concurrency testing practical and efficient for JVM programs. In an empirical evaluation on 53 benchmark programs with known bugs (SCTBench and JaConTeBe), Fray with random search finds 70% more bugs than JPF and 77% more bugs than RR's chaos mode. We also demonstrate Fray's push-button applicability on 2,655 tests from Apache Kafka, Lucene, and Google Guava. In these mature projects, Fray successfully discovered 18 real-world concurrency bugs that can cause 363 tests to fail reproducibly.

cs.PL↗

arXiv2024

Can Large Language Models Write Good Property-Based Tests?

Property-based testing (PBT), while an established technique in the software testing research community, is still relatively underused in real-world software. Pain points in writing property-based tests include implementing diverse random input generators and thinking of meaningful properties to test. Developers, however, are more amenable to writing documentation; plenty of library API documentation is available and can be used as natural language specifications for PBTs. As large language models (LLMs) have recently shown promise in a variety of coding tasks, we investigate using modern LLMs to automatically synthesize PBTs using two prompting techniques. A key challenge is to rigorously evaluate the LLM-synthesized PBTs. We propose a methodology to do so considering several properties of the generated tests: (1) validity, (2) soundness, and (3) property coverage, a novel metric that measures the ability of the PBT to detect property violations through generation of property mutants. In our evaluation on 40 Python library API methods across three models (GPT-4, Gemini-1.5-Pro, Claude-3-Opus), we find that with the best model and prompting approach, a valid and sound PBT can be synthesized in 2.4 samples on average. We additionally find that our metric for determining soundness of a PBT is aligned with human judgment of property assertions, achieving a precision of 100% and recall of 97%. Finally, we evaluate the property coverage of LLMs across all API methods and find that the best model (GPT-4) is able to automatically synthesize correct PBTs for 21% of properties extractable from API documentation.

cs.SE↗

arXiv2021

Growing a Test Corpus with Bonsai Fuzzing

This paper presents a coverage-guided grammar-based fuzzing technique for automatically generating a corpus of concise test inputs for programs such as compilers. We walk-through a case study of a compiler designed for education and the corresponding problem of generating meaningful test cases to provide to students. The prior state-of-the-art solution is a combination of fuzzing and test-case reduction techniques such as variants of delta-debugging. Our key insight is that instead of attempting to minimize convoluted fuzzer-generated test inputs, we can instead grow concise test inputs by construction using a form of iterative deepening. We call this approach Bonsai Fuzzing. Experimental results show that Bonsai Fuzzing can generate test corpora having inputs that are 16--45% smaller in size on average as compared to a fuzz-then-reduce approach, while achieving approximately the same code coverage and fault-detection capability.

cs.SE↗