Concolic execution is a practical test generation technique that explores execution paths by coupling concrete execution with symbolic reasoning. It runs programs on given inputs while capturing symbolic path representations, then mutates and solves these constraints to generate new test inputs for alternative paths. This approach has several fundamental challenges, such as (C1) the inherent complexity of symbolically modeling diverse programming language constructs and environmental interactions, and (C2) the scalability issues of constraint solvers when handling large, complex formulas. In this work, we investigate whether LLM agents can help address these longstanding challenges in test generation. We propose a novel workflow which we call agentic concolic execution. Using an LLM agent for symbolization, our approach is language-agnostic and can handle environmental constraints without additional manual modeling effort. To ease pressure on the constraint solver, we allow an LLM agent to summarize and even reason about constraints directly in natural language. In a significant evaluation of 12 real-world subjects, our research prototype CONCOLLMIC attains significantly higher code coverage (115%-233% higher) than state-of-the-art symbolic executors like KLEE that have been painstakingly hand-crafted over many years, and identifies 11 new vulnerabilities. Our results show that multi-step planning and tool integration enable agents to effectively mitigate reliability issues inherent in LLM-based analysis and even reason symbolically about code.

Protocol fuzzing is an effective technique for discovering vulnerabilities in protocol implementations. Although much progress has been made in optimizing input mutation, the initial seed inputs, which serve as the starting point for fuzzing, are still a critical factor in determining the effectiveness of subsequent fuzzing. Existing methods for seed corpus preparation mainly rely on captured network traffic, which suffers from limited diversity due to the biased message distributions present in real-world traffic. Protocol specifications encompass detailed information on diverse messages and thus provide a more comprehensive way for seed corpus preparation. However, these specifications are voluminous and not directly machine-readable.To address this challenge, we introduce PSG, which enhances protocol fuzzing by leveraging large language models (LLMs) to analyze protocol specifications for generating a high-quality seed corpus. First, PSG systematically reorganizes the protocol specification metadata into a structured knowledge base for effective LLM augmentation. Then, PSG employs a grammar-free method to generate target protocol messages and incorporates an iterative refinement process for better accuracy and efficiency. Our evaluation on 7 widely-used protocols and 13 implementations demonstrates that PSG can effectively generate diverse, protocol-compliant message inputs. Moreover, the generated seed corpus significantly improves the performance of state-of-the-art black-box and grey-box protocol fuzzers, achieving higher branch coverage and discovering more zero-day bugs.

Protocols in autonomous vehicles are essential for efficient in-vehicle network communication. To ensure their security, many research efforts have been paid to the fuzz testing of their implementations. However, those fuzzing optimizations often struggle to manage the protocols' complex state, resulting in low efficiency in branch covering and vulnerability detection.

Network protocol reverse engineering is crucial for a wide range of security applications. Many existing techniques accomplish this task by analyzing network traces. However, these methods globally cluster messages and analyze each cluster separately, which causes the loss of valuable field information. To address this problem, we present MDIplier, a protocol reverse engineering tool that leverages the hierarchical structure of protocol messages and performs tailored analysis at each message layer. MDIplier performs an iterative inference process. During each iteration, it identifies the message delimiter for layer separation and infers the format for each layer separately, optimizing the use of available field information. Our evaluation of eight widely used protocols shows that MDIplier outperforms state-of-the-art methods. It identifies fields with a perfection score 4.6×, 1.4×, 5.8×, and 1.8× higher than that of Netzob, Netplier, FieldHunter, and BinaryInferno, respectively. Furthermore, the experiments on proprietary protocols used in three IoT devices demonstrate the effectiveness of MDIplier in real-world scenarios.

Network protocols are extensively used in a variety of network devices, making the security of their implementations crucial. Protocol fuzzing has shown promise in uncovering vulnerabilities in these implementations. However traditional methods often require instrumentation of the target implementation to provide guidance, which is intrusive, adds overhead, and can hinder black-box testing. This paper presents Logos, a protocol fuzzer that utilizes non-intrusive runtime log information for fuzzing guidance. Logos first standardizes the unstructured logs and embeds them into a high-dimensional vector space for semantic representation.Then, Logos filters the semantic representation and dynamically maintains a semantic coverage to chart the explored space for customized guidance.We evaluate Logos on eight widely used implementations of well-known protocols. Results show that, compared to existing intrusive or expert knowledge-driven protocol fuzzers, Logos achieves 26.75%-106.19% higher branch coverage within 24 hours. Furthermore, Logos exposed 12 security-critical vulnerabilities in these prominent protocol implementations, with 9 CVEs assigned.

Internet of Things (IoT) messaging protocols play an important role in facilitating communications between users and IoT devices. Mainstream IoT platforms employ brokers, server-side implementations of IoT messaging protocols, to enable and mediate this user-device communication. Due to the complex nature of managing communications among devices with diverse roles and functionalities, comprehensive testing of the protocol brokers necessitates collaborative parallel fuzzing. However, being unaware of the relationship between test packets generated by different parties, existing parallel fuzzing methods fail to explore the brokers’ diverse processing logic effectively. This article introduces MPFuzz, a parallel fuzzing tool designed to secure IoT messaging protocols through collaborative packet generation. The approach leverages the critical role of certain fields within IoT messaging protocols that specify the logic for message forwarding and processing by protocol brokers. MPFuzzemploys an information synchronization mechanism to synchronize these key fields across different fuzzing instances and introduces a semantic-aware refinement module that optimizes generated test packets by utilizing the shared information and field semantics. This strategy facilitates a collaborative refinement of test packets across otherwise isolated fuzzing instances, thereby boosting the efficiency of parallel fuzzing. We evaluated MPFuzzon six widely used IoT messaging protocol implementations. Compared to two state-of-the-art protocol fuzzers with parallel capabilities, Peach and AFLNet, as well as two representative parallel fuzzers, SPFuzz and AFLTeam, MPFuzzachieves (6.1%,$174.5\times $), (20.2%,$607.2\times $), (1.9%,$4.1\times $), and (17.4%,$570.2\times $) higher branch coverage and fuzzing speed under the same computing resource. Furthermore, MPFuzzexposed seven previously unknown vulnerabilities in these extensively tested projects, all of which have been assigned with CVE identifiers.

Industrial control system (ICS) employs complex multistate protocols to realize high-reliability communication and intelligent control over automation equipment. ICS has been widely used in various embedded fields, such as autonomous vehicle systems, power automation systems, etc. However, in recent years, many attacks have been performed on ICS, especially its protocols, such as the hijacks over Jeep Uconnect and Tesla Autopilot autonomous systems, also the Stuxnet and DragonFly viruses over national infrastructures. It is important to guarantee the security of ICS protocols. In this article, we presentCharon, an efficient fuzzing platform for the vulnerability detection of ICS protocol implementations. InCharon, we propose an innovative fuzzing strategy that leverages state guidance to maximize cross-state code coverage instead of focusing on isolated states during the fuzzing of ICS protocols. Moreover, we devise a novel feedback collection method that employs program status inferring to avoid the restart of the ICS protocol at each iteration, allowing for continuous fuzzing. We evaluateCharonon several popular ICS protocol implementations, including real-time publish subscribe, IEC61850-MMS, MQTT, etc. Compared with typical fuzzers, such as American fuzzy lop, Polar, AFLNET, Boofuzz, and Peach, it averagely improves branch coverage by 234.2%, 194.4%, 215.9%, 52.58%, and 35.18%, respectively. Moreover, it has already confirmed 21 previously unknown vulnerabilities (e.g., stack buffer overflow) among these ICS protocols, most of which are security critical and corresponding patches from vendors have been released accordingly.

The rapid development of in-vehicle networks and protocols brings efficient communication service but also increases the risk of attack. Any vulnerability may be leveraged to cause serious consequences. It is of vital importance to guarantee their security. However, the vulnerability detection efficiency of traditional techniques such as fuzzing is challenged by the complex relations among protocol states.In this paper, we propose PAVFuzz, a state-sensitive fuzz testing framework to secure those protocols used in autonomous vehicles. It automatically learns relations between two data elements in different protocol states. The relations will then be used to calculate and update the mutation weight of each data element continuously. Accordingly, PAVFuzz is able to select the target data elements and perform state-sensitive mutation to boost the efficiency. Experiments show that, compared with state-of-the-art fuzzers Peach and AFL, PAVFuzz increases branch coverage by averagely 22.51% and 369.19% within 24 hours. It has successfully exposed 12 serious previously unknown vulnerabilities among several protocols that are widely used in autonomous vehicles, such as RTPS and SOME/IP. We have reported them to the developers and corresponding patches have been released.

Industrial Control System (ICS) protocols play an essential role in building communications among system components. Recently, many severe vulnerabilities, such as Stuxnet and DragonFly, exposed in ICS protocols have affected a wide distribution of devices. Therefore, it is of vital importance to ensure their correctness. However, the vulnerability detection efficiency of traditional techniques such as fuzzing is challenged by the complexity and diversity of the protocols.In this paper, we propose to equip the traditional protocol fuzzing with coverage-guided packet crack and generation. We collect the coverage information during the testing procedure, save those valuable packets that trigger new path coverage and crack them into pieces, based on which, we can construct higher-quality new packets for further testing. For evaluation, we build Peach*on top of Peach, which is one of the most widely used protocol fuzzers, and conduct experiments on several ICS protocols such as Modbus and DNP3. Results show that, compared with the original Peach, Peach*achieves the same code coverage and bug detection numbers at the speed of 1.2X-25X. It also gains final increase with 8.35%-36.84% more paths within 24 hours and has exposed 9 previously unknown vulnerabilities.

Industrial Control System (ICS) protocols are widely used to build communications among system components. Compared with common internet protocols, ICS protocols have more control over remote devices by carrying a specific field called “function code”, which assigns what the receive end should do. Therefore, it is of vital importance to ensure their correctness. However, traditional vulnerability detection techniques such as fuzz testing are challenged by the increasing complexity of these diverse ICS protocols. In this paper, we present a function code aware fuzzing framework — Polar, which automatically extracts semantic information from the ICS protocol and utilizes this information to accelerate security vulnerability detection. Based on static analysis and dynamic taint analysis, Polar initiates the values of the function code field and identifies some vulnerable operations. Then, novel semantic aware mutation and selection strategies are designed to optimize the fuzzing procedure. For evaluation, we implement Polar on top of two popular fuzzers — AFL and AFLFast, and conduct experiments on several widely used ICS protocols such as Modbus, IEC104, and IEC 61850. Results show that, compared with AFL and AFLFast, Polar achieves the same code coverage and bug detection numbers at the speed of 1.5X-12X. It also gains increase with 0%--91% more paths within 24 hours. Furthermore, Polar has exposed 10 previously unknown vulnerabilities in those protocols, 6 of which have been assigned unique CVE identifiers in the US National Vulnerability Database.