Coverage-guided fuzzing's aggressive, high-volume testing has helped reveal tens of thousands of software security flaws. While executing billions of test cases mandates fast code coverage tracing, the nature of binary-only targets leads to reduced tracing performance. A recent advancement in binary fuzzing performance is Coverage-guided Tracing (CGT), which brings orders-of-magnitude gains in throughput by restricting the expense of coverage tracing to only when new coverage is guaranteed. Unfortunately, CGT suits only a basic block coverage granularity---yet most fuzzers require finer-grain coverage metrics: edge coverage and hit counts. It is this limitation which prohibits nearly all of today's state-of-the-art fuzzers from attaining the performance benefits of CGT.This paper tackles the challenges of adapting CGT to fuzzing's most ubiquitous coverage metrics. We introduce and implement a suite of enhancements that expand CGT's introspection to fuzzing's most common code coverage metrics, while maintaining its orders-of-magnitude speedup over conventional always-on coverage tracing. We evaluate their trade-offs with respect to fuzzing performance and effectiveness across 12 diverse real-world binaries (8 open- and 4 closed-source). On average, our coverage-preserving CGT attains near-identical speed to the present block-coverage-only CGT, UnTracer; and outperforms leading binary- and source-level coverage tracers QEMU, Dyninst, RetroWrite, and AFL-Clang by 2--24x, finding more bugs in less time.
more »
« less
Facilitating Parallel Fuzzing with Mutually-exclusive Task Distribution
Fuzz testing, or fuzzing, has become one of the de facto standard techniques for bug finding in the software industry. In general, fuzzing provides various inputs to the target program with the goal of discovering unhandled exceptions and crashes. In business sectors where the time budget is limited, software vendors often launch many fuzzing instances in parallel as a common means of increasing code coverage. However, most of the popular fuzzing tools — in their parallel mode — naively run multiple instances concurrently, without elaborate distribution of workload. This can lead different instances to explore overlapped code regions, eventually reducing the benefits of concurrency. In this paper, we propose a general model to describe parallel fuzzing. This model distributes mutually-exclusive but similarly-weighted tasks to different instances, facilitating concurrency and also fairness across instances. Following this model, we develop a solution, called AFL-EDGE, to improve the parallel mode of AFL, considering a round of mutations to a unique seed as a task and adopting edge coverage to define the uniqueness of a seed. We have implemented AFL-EDGE on top of AFL and evaluated the implementation with AFL on 9 widely used benchmark programs. It shows that AFL-EDGE can benefit the edge coverage of AFL. In a 24-hour test, the increase of edge coverage brought by AFL-EDGE to AFL ranges from 9.5% to 10.2%, depending on the number of instances. As a side benefit, we discovered 14 previously unknown bugs.
more »
« less
- Award ID(s):
- 2031377
- NSF-PAR ID:
- 10298070
- Date Published:
- Journal Name:
- 17th EAI International Conference on Security and Privacy in Communication Networks
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Coverage-guided fuzzing is one of the most effective software security testing techniques. Fuzzing takes on one of two forms: compiler-based or binary-only, depending on the availability of source code. While the fuzzing community has improved compiler-based fuzzing with performance- and feedback-enhancing program transformations, binary-only fuzzing lags behind due to the semantic and performance limitations of instrumenting code at the binary level. Many fuzzing use cases are binary-only (i.e., closed source). Thus, applying fuzzing-enhancing program transformations to binary-only fuzzing—without sacrificing performance—remains a compelling challenge. This paper examines the properties required to achieve compiler-quality binary-only fuzzing instrumentation. Based on our findings, we design ZAFL: a platform for applying fuzzing-enhancing program transformations to binary-only targets—maintaining compiler-level performance. We showcase ZAFL's capabilities in an implementation for the popular fuzzer AFL, including five compiler-style fuzzing-enhancing transformations, and evaluate it against the leading binary-only fuzzing instrumenters AFL-QEMU and AFL-Dyninst. Across LAVA-M and real-world targets, ZAFL improves crash-finding by 26–96% and 37–131%; and throughput by 48– 78% and 159–203% compared to AFL-Dyninst and AFL-QEMU, respectively—while maintaining compiler-level of overhead of 27%. We also show that ZAFL supports real-world open- and closed-source software of varying size (10K– 100MB), complexity (100–1M basic blocks), platform (Linux and Windows), and format (e.g., stripped and PIC).more » « less
-
Detecting regression bugs in software evolution, analyzing side-channels in programs and evaluating robustness in deep neural networks (DNNs) can all be seen as instances of differential software analysis, where the goal is to generate diverging executions of program paths. Two executions are said to be diverging if the observable program behavior differs, e.g., in terms of program output, execution time, or (DNN) classification. The key challenge of differential software analysis is to simultaneously reason about multiple program paths, often across program variants. This paper presents HyDiff, the first hybrid approach for differential software analysis. HyDiff integrates and extends two very successful testing techniques: Feedback-directed greybox fuzzing for efficient program testing and shadow symbolic execution for systematic program exploration. HyDiff extends greybox fuzzing with divergence-driven feedback based on novel cost metrics that take into account the control flow graph of the program. Furthermore HyDiff extends shadow symbolic execution by applying four-way forking in a systematic exploration and still having the ability to incorporate concrete inputs in the analysis. HyDiff applies divergence revealing heuristics based on resource consumption and control-flow information to efficiently guide the symbolic exploration, which allows its efficient usage beyond regression testing applications. We introduce differential metrics such as output, decision and cost difference, as well as patch distance, to assist the fuzzing and symbolic execution components in maximizing the execution divergence. We implemented our approach on top of the fuzzer AFL and the symbolic execution framework Symbolic PathFinder. We illustrate HyDiff on regression and side-channel analysis for Java bytecode programs, and further show how to use HyDiff for robustness analysis of neural networks.more » « less
-
As specialized hardware accelerators like FPGAs become a prominent part of the current computing landscape, software applications are increasingly constructed to leverage heterogeneous architectures. Such a trend is already happening in the domain of machine learning and Internet-of-Things (IoT) systems built on edge devices. Yet, debugging and testing methods for heterogeneous applications are currently lacking. These applications may look similar to regular C/C++ code but include hardware synthesis details in terms of preprocessor directives. Therefore, their behavior under heterogeneous architectures may diverge significantly from CPU due to hardware synthesis details. Further, the compilation and hardware simulation cycle takes an enormous amount of time, prohibiting frequent invocations required for fuzz testing. We propose a novel fuzz testing technique, called HeteroFuzz, designed to specifically target heterogeneous applications and to detect platform-dependent divergence. The key essence of HeteroFuzz is that it uses a three-pronged approach to reduce the long latency of repetitively invoking a hardware simulator on a heterogeneous application. First, in addition to monitoring code coverage as a fuzzing guidance mechanism, we analyze synthesis pragmas in kernel code and monitor accelerator-relevant value spectra. Second, we design dynamic probabilistic mutations to increase the chance of hitting divergent behavior under different platforms. Third, we memorize the boundaries of seen kernel inputs and skip HLS simulator invocation if it can expose only redundant divergent behavior. We evaluate HeteroFuzz on seven real-world heterogeneous applications with FPGA kernels. HeteroFuzz is 754X faster in exposing the same set of distinct divergence symptoms than naive fuzzing. Probabilistic mutations contribute to 17.5X speed up than the one without. Selective invocation of HLS simulation contributes to 8.8X speed up than the one without.more » « less
-
Fuzzing reliably and efficiently finds bugs in software, including operating system kernels. In general, higher code coverage leads to the discovery of more bugs. This is why most existing kernel fuzzers adopt strategies to generate a series of inputs that attempt to greedily maximize the amount of code that they exercise. However, simply executing code may not be sufficient to reveal bugs that require specific sequences of actions. Synthesizing inputs to trigger such bugs depends on two aspects: (i) the actions the executed code takes, and (ii) the order in which those actions are taken. An action is a high-level operation, such as a heap allocation, that is performed by the executed code and has a specific semantic meaning. ACTOR, our action-guided kernel fuzzing framework, deviates from traditional methods. Instead of focusing on code coverage optimization, our approach generates fuzzer programs (inputs) that leverage our understanding of triggered actions and their temporal relationships. Specifically, we first capture actions that potentially operate on shared data structures at different times. Then, we synthesize programs using those actions as building blocks, guided by bug templates expressed in our domain-specific language. We evaluated ACTOR on four different versions of the Linux kernel, including two well-tested and frequently updated long-term (5.4.206, 5.10.131) versions, a stable (5.19), and the latest (6.2-rc5) release. Our evaluation revealed a total of 41 previously unknown bugs, of which 9 have already been fixed. Interestingly, 15 (36.59%) of them were discovered in less than a day.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
