ConFL: Constraint-guided Fuzzing for Machine Learning Framework

by   Zhao Liu, et al.

As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) frameworks. Nevertheless, testing these frameworks is a daunting task due to their intricate implementation. Previous research on fuzzing ML frameworks has struggled to effectively extract input constraints and generate valid inputs, leading to extended fuzzing durations for deep execution or revealing the target crash. In this paper, we propose ConFL, a constraint-guided fuzzer for ML frameworks. ConFL automatically extracting constraints from kernel codes without the need for any prior knowledge. Guided by the constraints, ConFL is able to generate valid inputs that can pass the verification and explore deeper paths of kernel codes. In addition, we design a grouping technique to boost the fuzzing efficiency. To demonstrate the effectiveness of ConFL, we evaluated its performance mainly on Tensorflow. We find that ConFL is able to cover more code lines, and generate more valid inputs than state-of-the-art (SOTA) fuzzers. More importantly, ConFL found 84 previously unknown vulnerabilities in different versions of Tensorflow, all of which were assigned with new CVE ids, of which 3 were critical-severity and 13 were high-severity. We also extended ConFL to test PyTorch and Paddle, 7 vulnerabilities are found to date.


page 1

page 2

page 3

page 4


Leveraging Documentation to Test Deep Learning Library Functions

It is integral to test API functions of widely used deep learning (DL) l...

IvySyn: Automated Vulnerability Discovery for Deep Learning Frameworks

We present IvySyn: the first fully-automated framework for vulnerability...

Characterizing and Understanding Software Security Vulnerabilities in Machine Learning Libraries

The application of machine learning (ML) libraries has been tremendously...

ACETest: Automated Constraint Extraction for Testing Deep Learning Operators

Deep learning (DL) applications are prevalent nowadays as they can help ...

Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

In the context of aircraft system performance assessment, deep learning ...

HDTest: Differential Fuzz Testing of Brain-Inspired Hyperdimensional Computing

Brain-inspired hyperdimensional computing (HDC) is an emerging computati...

MinUn: Accurate ML Inference on Microcontrollers

Running machine learning inference on tiny devices, known as TinyML, is ...

Please sign up or login with your details

Forgot password? Click here to reset