An official website of the United States government
Detecting software vulnerabilities has been a challenge for decades. Many techniques have been developed to detect vulnerabilities by reporting whether a vulnerability exists in the code of software. But few of them have the capability to categorize the types of detected vulnerabilities, which is crucial for human developers or other tools to analyze and address vulnerabilities. In this paper, we present our work on identifying the types of vulnerabilities using deep learning. Our data consists of code slices parsed in a manner that captures the syntax and semantics of a vulnerability, sourced from prior work. We train deep neural networks on these features to perform multiclass classification of software vulnerabilities in the dataset. Our experiments show that our models can effectively identify the vulnerability classes of the vulnerable functions in our dataset.
more »
« less
Interpreting Deep Learning-based Vulnerability Detector Predictions Based on Heuristic Searching
Detecting software vulnerabilities is an important problem and a recent development in tackling the problem is the use of deep learning models to detect software vulnerabilities. While effective, it is hard to explain why a deep learning model predicts a piece of code as vulnerable or not because of the black-box nature of deep learning models. Indeed, the interpretability of deep learning models is a daunting open problem. In this article, we make a significant step toward tackling the interpretability of deep learning model in vulnerability detection. Specifically, we introduce a high-fidelity explanation framework, which aims to identify a small number of tokens that make significant contributions to a detector’s prediction with respect to an example. Systematic experiments show that the framework indeed has a higher fidelity than existing methods, especially when features are not independent of each other (which often occurs in the real world). In particular, the framework can produce some vulnerability rules that can be understood by domain experts for accepting a detector’s outputs (i.e., true positives) or rejecting a detector’s outputs (i.e., false-positives and false-negatives). We also discuss limitations of the present study, which indicate interesting open problems for future research.
more »
« less
- PAR ID:
- 10281044
- Date Published:
- Journal Name:
- ACM Transactions on Software Engineering and Methodology
- Volume:
- 30
- Issue:
- 2
- ISSN:
- 1049-331X
- Page Range / eLocation ID:
- 1 to 31
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Detecting security vulnerabilities in software before they are exploited has been a challenging problem for decades. Traditional code analysis methods have been proposed, but are often ineffective and inefficient. In this work, we model software vulnerability detection as a natural language processing (NLP) problem with source code treated as texts, and address the auto-mated software venerability detection with recent advanced deep learning NLP models assisted by transfer learning on written English. For training and testing, we have preprocessed the NIST NVD/SARD databases and built a dataset of over 100,000 files in C programming language with 123 types of vulnerabilities. The extensive experiments generate the best performance of over 93% accuracy in detecting security vulnerabilities.more » « less
-
null (Ed.)Numerous cloud-based services are provided to help customers develop and deploy deep learning applications. When a customer deploys a deep learning model in the cloud and serves it to end-users, it is important to be able to verify that the deployed model has not been tampered with. In this paper, we propose a novel and practical methodology to verify the integrity of remote deep learning models, with only black-box access to the target models. Specifically, we define Sensitive-Sample fingerprints, which are a small set of human unnoticeable transformed inputs that make the model outputs sensitive to the model's parameters. Even small model changes can be clearly reflected in the model outputs. Experimental results on different types of model integrity attacks show that we proposed approach is both effective and efficient. It can detect model integrity breaches with high accuracy (>99.95%) and guaranteed zero false positives on all evaluated attacks. Meanwhile, it only requires up to 103× fewer model inferences, compared with non-sensitive samples.more » « less
-
In high-level Autonomous Driving (AD) systems, behavioral planning is in charge of making high-level driving decisions such as cruising and stopping, and thus highly securitycritical. In this work, we perform the first systematic study of semantic security vulnerabilities specific to overly-conservative AD behavioral planning behaviors, i.e., those that can cause failed or significantly-degraded mission performance, which can be critical for AD services such as robo-taxi/delivery. We call them semantic Denial-of-Service (DoS) vulnerabilities, which we envision to be most generally exposed in practical AD systems due to the tendency for conservativeness to avoid safety incidents. To achieve high practicality and realism, we assume that the attacker can only introduce seemingly-benign external physical objects to the driving environment, e.g., off-road dumped cardboard boxes. To systematically discover such vulnerabilities, we design PlanFuzz, a novel dynamic testing approach that addresses various problem-specific design challenges. Specifically, we propose and identify planning invariants as novel testing oracles, and design new input generation to systematically enforce problemspecific constraints for attacker-introduced physical objects. We also design a novel behavioral planning vulnerability distance metric to effectively guide the discovery. We evaluate PlanFuzz on 3 planning implementations from practical open-source AD systems, and find that it can effectively discover 9 previouslyunknown semantic DoS vulnerabilities without false positives. We find all our new designs necessary, as without each design, statistically significant performance drops are generally observed. We further perform exploitation case studies using simulation and real-vehicle traces. We discuss root causes and potential fixes.more » « less
-
Mainstream software applications and tools are the configurable platforms with an enormous number of parameters along with their values. Certain settings and possible interactions between these parameters may harden (or soften) the security and robustness of these applications against some known vulnerabilities. However, the large number of vulnerabilities reported and associated with these tools make the exhaustive testing of these tools infeasible against these vulnerabilities infeasible. As an instance of general software testing problem, the research question to address is whether the system under test is robust and secure against these vulnerabilities. This paper introduces the idea of "vulnerability coverage," a concept to adequately test a given application for a certain classes of vulnerabilities, as reported by the National Vulnerability Database (NVD). The deriving idea is to utilize the Common Vulnerability Scoring System (CVSS) as a means to measure the fitness of test inputs generated by evolutionary algorithms and then through pattern matching identify vulnerabilities that match the generated vulnerability vectors and then test the system under test for those identified vulnerabilities. We report the performance of two evolutionary algorithms (i.e., Genetic Algorithms and Particle Swarm Optimization) in generating the vulnerability pattern vectors.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3429444
