Security Knowledge-Guided Fuzzing of Deep Learning Libraries

• URL: http://arxiv.org/abs/2306.03269v2
• Date: Sun, 24 Dec 2023 23:50:31 GMT
• Title: Security Knowledge-Guided Fuzzing of Deep Learning Libraries
• Authors: Nima Shiri Harzevili, Mohammad Mahdi Mohajer, Moshi Wei, Hung Viet Pham, Song Wang
• Abstract summary: We propose a novel Deep Learning fuzzer named Orion. Orion combines guided test input generation and corner case test input generation based on a set of fuzzing rules.
• Score: 9.930638894226004
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, many Deep Learning fuzzers have been proposed for testing of DL libraries. However, they either perform unguided input generation (e.g., not considering the relationship between API arguments when generating inputs) or only support a limited set of corner case test inputs. Furthermore, a substantial number of developer APIs crucial for library development remain untested, as they are typically not well-documented and lack clear usage guidelines. To fill this gap, we propose a novel fuzzer named Orion, which combines guided test input generation and corner case test input generation based on a set of fuzzing rules constructed from historical data that is known to trigger vulnerabilities in the implementation of DL APIs. To extract the fuzzing rules, we first conduct an empirical study regarding the root cause analysis of 376 vulnerabilities in two of the most popular DL libraries, i.e., PyTorch and TensorFlow. We then construct the rules based on the root causes of the historical vulnerabilities. Our evaluation shows that Orion reports 135 vulnerabilities on the latest releases of TensorFlow and PyTorch, 76 of which were confirmed by the library developers. Among the 76 confirmed vulnerabilities, 69 are previously unknown, and 7 have already been fixed. The rest are awaiting further confirmation. Regarding end-user APIs, Orion was able to detect 31.8% and 90% more vulnerabilities on TensorFlow and PyTorch, respectively, compared to the state-of-the-art conventional fuzzer, i.e., DeepRel. When compared to the state-of-the-art LLM-based DL fuzzer, AtlasFuzz, Orion detected 13.63% more vulnerabilities on TensorFlow and 18.42% more vulnerabilities on PyTorch. Regarding developer APIs, Orion stands out by detecting 117% more vulnerabilities on TensorFlow and 100% more vulnerabilities on PyTorch compared to the most relevant fuzzer designed for developer APIs, such as FreeFuzz.

Related papers

• In the Magma chamber: Update and challenges in ground-truth vulnerabilities revival for automatic input generator comparison [42.95491588006701]
  Magma introduced the notion of forward-porting to reintroduce vulnerable code in current software releases. While their results are promising, the state-of-the-art lacks an update on the maintainability of this approach over time. We characterise the challenges with forward-porting by reassessing the portability of Magma's CVEs four years after its release.
  arXiv  Detail & Related papers  (2025-03-25T17:59:27Z)
• Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models [49.214291813478695]
  Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like overflows and use buffer-free errors. Traditional fuzzing struggles with the complexity and API diversity of DL libraries. We propose DFUZZ, an LLM-driven fuzzing approach for DL libraries.
  arXiv  Detail & Related papers  (2025-01-08T07:07:22Z)
• Subgraph-Oriented Testing for Deep Learning Libraries [9.78188667672054]
  We propose SORT (Subgraph-Oriented Realistic Testing) to test Deep Learning (DL) libraries on different hardware platforms. SORT takes popular API interaction patterns, represented as frequent subgraphs of model graphs, as test subjects. SORT achieves a 100% valid input generation rate, detects more precision bugs than existing methods, and reveals interaction-related bugs missed by single-API testing.
  arXiv  Detail & Related papers  (2024-12-09T12:10:48Z)
• The Seeds of the FUTURE Sprout from History: Fuzzing for Unveiling Vulnerabilities in Prospective Deep-Learning Libraries [14.260990784121423]
  Future is the first universal fuzzing framework tailored for newly introduced and prospective DL libraries. It uses historical bug information from existing libraries and fine-tunes LLMs for specialized code generation. It significantly outperforms existing fuzzers in bug detection, success rate of bug reproduction, validity rate of code generation, and API coverage.
  arXiv  Detail & Related papers  (2024-12-02T09:33:28Z)
• Discovery of Timeline and Crowd Reaction of Software Vulnerability Disclosures [47.435076500269545]
  Apache Log4J was found to be vulnerable to remote code execution attacks. More than 35,000 packages were forced to update their Log4J libraries with the latest version. It is practically reasonable for software developers to update their third-party libraries whenever the software vendors have released a vulnerable-free version.
  arXiv  Detail & Related papers  (2024-11-12T01:55:51Z)
• FuzzTheREST: An Intelligent Automated Black-box RESTful API Fuzzer [0.0]
  This work introduces a black-box API of fuzzy testing tool that employs Reinforcement Learning (RL) for vulnerability detection. The tool found a total of six unique vulnerabilities and achieved 55% code coverage.
  arXiv  Detail & Related papers  (2024-07-19T14:43:35Z)
• A Classification-by-Retrieval Framework for Few-Shot Anomaly Detection to Detect API Injection Attacks [9.693391036125908]
  We propose a novel unsupervised few-shot anomaly detection framework composed of two main parts. First, we train a dedicated generic language model for API based on FastText embedding. Next, we use Approximate Nearest Neighbor search in a classification-by-retrieval approach.
  arXiv  Detail & Related papers  (2024-05-18T10:15:31Z)
• A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish [47.3916421056009]
  Large Language Models (LLMs) are trained on massive web-crawled corpora. LLMs produce leaked information in most cases despite less such data in their training set. Self-detection method showed superior performance compared to existing detection methods.
  arXiv  Detail & Related papers  (2024-03-24T13:21:58Z)
• Benchmarking Deep Learning Fuzzers [11.118370064698869]
  We run three state-of-the-art DL fuzzers, FreeFuzz, DeepRel, and DocTer, on the benchmark by following their instructions. We find that these fuzzers are unable to detect many real bugs collected in our benchmark dataset. Our systematic analysis further identifies four major, broad, and common factors that affect these fuzzers' ability to detect real bugs.
  arXiv  Detail & Related papers  (2023-10-10T18:09:16Z)
• SyzTrust: State-aware Fuzzing on Trusted OS Designed for IoT Devices [67.65883495888258]
  We present SyzTrust, the first state-aware fuzzing framework for vetting the security of resource-limited Trusted OSes. SyzTrust adopts a hardware-assisted framework to enable fuzzing Trusted OSes directly on IoT devices. We evaluate SyzTrust on Trusted OSes from three major vendors: Samsung, Tsinglink Cloud, and Ali Cloud.
  arXiv  Detail & Related papers  (2023-09-26T08:11:38Z)
• On the Security Blind Spots of Software Composition Analysis [46.1389163921338]
  We present a novel approach to detect vulnerable clones in the Maven repository. We retrieve over 53k potential vulnerable clones from Maven Central. We detect 727 confirmed vulnerable clones and synthesize a testable proof-of-vulnerability project for each of those.
  arXiv  Detail & Related papers  (2023-06-08T20:14:46Z)
• EDEFuzz: A Web API Fuzzer for Excessive Data Exposures [3.5061201620029885]
  Excessive Data Exposure (EDE) was the third most significant API vulnerability of 2019. There are few automated tools -- either in research or industry -- to effectively find and remediate such issues. We build the first fuzzing tool -- that we call EDEFuzz -- to systematically detect EDEs.
  arXiv  Detail & Related papers  (2023-01-23T04:05:08Z)
• REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service [67.0982378001551]
  We show how a service provider pre-trains an encoder and then deploys it as a cloud service API. A client queries the cloud service API to obtain feature vectors for its training/testing inputs. We show that the cloud service only needs to provide two APIs to enable a client to certify the robustness of its downstream classifier.
  arXiv  Detail & Related papers  (2023-01-07T17:40:11Z)
• Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection [69.59980270078067]
  We explore the untargeted backdoor watermarking scheme, where the abnormal model behaviors are not deterministic. We also discuss how to use the proposed untargeted backdoor watermark for dataset ownership verification.
  arXiv  Detail & Related papers  (2022-09-27T12:56:56Z)
• VUDENC: Vulnerability Detection with Deep Learning on a Natural Codebase for Python [8.810543294798485]
  VUDENC is a deep learning-based vulnerability detection tool. It learns features of vulnerable code from a large and real-world Python corpus. VUDENC achieves a recall of 78%-87%, a precision of 82%-96%, and an F1 score of 80%-90%.
  arXiv  Detail & Related papers  (2022-01-20T20:29:22Z)
• Detection as Regression: Certified Object Detection by Median Smoothing [50.89591634725045]
  This work is motivated by recent progress on certified classification by randomized smoothing. We obtain the first model-agnostic, training-free, and certified defense for object detection against $ell$-bounded attacks.
  arXiv  Detail & Related papers  (2020-07-07T18:40:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.