Crafting high-quality fuzz drivers not only is time-consuming but also requires a deep understanding of the library. However, the state-of-the-art automatic fuzz driver generation techniques fall short of expectations. While fuzz drivers derived from consumer code can reach deep states, they have limited coverage. Conversely, interpretative fuzzing can explore most API calls but requires numerous attempts within a large search space. We propose PromptFuzz, a coverage-guided fuzzer for prompt fuzzing that iteratively generates fuzz drivers to explore undiscovered library code. To explore API usage in fuzz drivers during prompt fuzzing, we propose several key techniques: instructive program generation, erroneous program validation, coverage-guided prompt mutation, and constrained fuzzer scheduling. We implemented PromptFuzz and evaluated it on 14 real-world libraries. Compared with OSS-Fuzz and Hopper (the state-of-the-art fuzz driver generation tool), fuzz drivers generated by PromptFuzz achieved 1.61 and 1.63 times higher branch coverage than those by OSS-Fuzz and Hopper, respectively. Moreover, the fuzz drivers generated by PromptFuzz detected 33 genuine, new bugs out of a total of 49 crashes, out of which 30 bugs have been confirmed by their respective communities.

Despite the fact that the state-of-the-art fuzzers can generate inputs efficiently, existing fuzz drivers still cannot adequately cover entries in libraries. Most of these fuzz drivers are crafted manually by developers, and their quality depends on the developers' understanding of the code. Existing works have attempted to automate the generation of fuzz drivers by learning API usage from code and execution traces. However, the generated fuzz drivers are limited to a few specific call sequences by the code being learned. To address these challenges, we present HOPPER, which can fuzz libraries without requiring any domain knowledge to craft fuzz drivers. It transforms the problem of library fuzzing into the problem of interpreter fuzzing. The interpreters linked against libraries under test can interpret the inputs that describe arbitrary API usage. To generate semantically correct inputs for the interpreter, HOPPER learns the intra-and inter-API constraints in the libraries and mutates the program with grammar awareness. We implemented HOPPER and evaluated its effectiveness on 11 real-world libraries against manually crafted fuzzers and other automatic solutions. Our results show that HOPPER greatly outperformed the other fuzzers in both code coverage and bug finding, having uncovered 25 previously unknown bugs that other fuzzers couldn't. Moreover, we have demonstrated that the proposed intra- and inter-API constraint learning methods can correctly learn constraints implied by the library and, therefore, significantly improve the fuzzing efficiency. The experiment results indicate that HOPPER is able to explore a vast range of API usages for library fuzzing out of the box.

Existing tools for the automated detection of memory corruption bugs are not very effective in practice. They typically recognize only standard memory management (MM) APIs (e.g., malloc and free) and assume a naive paired-use model—an allocator is followed by a specific deallocator. However, we observe that programmers very often design their own MM functions and that these functions often manifest two major characteristics: (1) Custom allocator functions perform multi-object or nested allocation which then requires structure-aware deallocation functions. (2) Custom allocators and deallocators follow an unpaired-use model. A more effective detection thus needs to adapt those characteristics and capture memory bugs related to non-standard MM behaviors. In this paper, we present a MM function aware memory bug detection technique by introducing the concept of structure-aware and object-centric Memory Operation Synopsis (MOS). A MOS abstractly describes the memory objects of a given MM function, how they are managed by the function, and their structural relations. By utilizing MOS, a bug detection could explore much less code but is still capable of handling multi-object or nested allocations and does not rely on the paired-use model. In addition, to extensively find MM functions and automatically generate MOS for them, we propose a new identification approach that combines natural language processing (NLP) and data flow analysis, which enables the efficient and comprehensive identification of MM functions, even in very large code bases. We implement a MOS-enhanced memory bug detection system, Goshawk, to discover memory bugs caused by complex and custom MM behaviors. We applied Goshawk to well-tested and widely-used open source projects including OS kernels, server applications, and IoT SDKs. Goshawk outperforms the state-of-the-art data flow analysis driven bug detection tools by an order of magnitude in analysis speed and the number of accurately identified MM functions, reports the discovered bugs with a developer-friendly, MOS based description, and successfully detects 92 new double-free and use-after-free bugs.