Search

We present the design, implementation, and evaluation of FineIBT: a CFI enforcement mechanism that improves the precision of hardware-assisted CFI solutions, like Intel IBT, by instrumenting program code to reduce the valid/allowed targets of indirect forward-edge transfers. We study the design of FineIBT on the x86-64 architecture, and implement and evaluate it on Linux and the LLVM toolchain. We designed FineIBT's instrumentation to be compact, incurring low runtime and memory overheads, and generic, so as to support different CFI policies. Our prototype implementation incurs negligible runtime slowdowns ($\approx$0%-1.94% in SPEC CPU2017 and $\approx$0%-1.92% in real-world applications) outperforming Clang-CFI. Lastly, we investigate the effectiveness/security and compatibility of FineIBT using the ConFIRM CFI benchmarking suite, demonstrating that our instrumentation provides complete coverage in the presence of modern software features, while supporting a wide range of CFI policies with the same, predictable performance., Comment: Accepted at RAID 2023. Errata (reported by Lucas Becker): Section 2.4.1: "in which every bit represents 8 bytes of (virtual) memory" -> "in which two bits represent 16 bytes of (virtual) memory"

We present IvySyn, the first fully-automated framework for discovering memory error vulnerabilities in Deep Learning (DL) frameworks. IvySyn leverages the statically-typed nature of native APIs in order to automatically perform type-aware mutation-based fuzzing on low-level kernel code. Given a set of offending inputs that trigger memory safety (and runtime) errors in low-level, native DL (C/C++) code, IvySyn automatically synthesizes code snippets in high-level languages (e.g., in Python), which propagate error-triggering input via high(er)-level APIs. Such code snippets essentially act as "Proof of Vulnerability", as they demonstrate the existence of bugs in native code that an attacker can target through various high-level APIs. Our evaluation shows that IvySyn significantly outperforms past approaches, both in terms of efficiency and effectiveness, in finding vulnerabilities in popular DL frameworks. Specifically, we used IvySyn to test TensorFlow and PyTorch. Although still an early prototype, IvySyn has already helped the TensorFlow and PyTorch framework developers to identify and fix 61 previously-unknown security vulnerabilities, and assign 39 unique CVEs., Comment: Accepted at USENIX Security 2023

This paper introduces Pythia, the first fuzzer that augments grammar-based fuzzing with coverage-guided feedback and a learning-based mutation strategy for stateful REST API fuzzing. Pythia uses a statistical model to learn common usage patterns of a target REST API from structurally valid seed inputs. It then generates learning-based mutations by injecting a small amount of noise deviating from common usage patterns while still maintaining syntactic validity. Pythia's mutation strategy helps generate grammatically valid test cases and coverage-guided feedback helps prioritize the test cases that are more likely to find bugs. We present experimental evaluation on three production-scale, open-source cloud services showing that Pythia outperforms prior approaches both in code coverage and new bugs found. Using Pythia, we found 29 new bugs which we are in the process of reporting to the respective service owners.

Cloud services have recently exploded with the advent of powerful cloud-computing platforms such as Amazon Web Services and Microsoft Azure. Today, most cloud services are accessed through REST APIs, and Swagger is arguably the most popular interface-description language for REST APIs. A Swagger specification describes how to access a cloud service through its REST API (e.g., what requests the service can handle and what responses may be expected). This paper introduces REST-ler, the first automatic intelligent REST API security-testing tool. REST-ler analyzes a Swagger specification and generates tests that exercise the corresponding cloud service through its REST API. Each test is defined as a sequence of requests and responses. REST-ler generates tests intelligently by (1) inferring dependencies among request types declared in the Swagger specification (e.g., inferring that "a request B should not be executed before a request A" because B takes as an input argument a resource-id x returned by A) and by (2) analyzing dynamic feedback from responses observed during prior test executions in order to generate new tests (e.g., learning that "a request C after a request sequence A;B is refused by the service" and therefore avoiding this combination in the future). We show that these two techniques are necessary to thoroughly exercise a service under test while pruning the large search space of possible request sequences. We also discuss the application of REST-ler to test GitLab, a large popular open-source self-hosted Git service, and the new bugs that were found.

Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been shown to be vulnerable to sophisticated attacks. Recently a set of certified defenses have been introduced, which provide guarantees of robustness to norm-bounded attacks, but they either do not scale to large datasets or are limited in the types of models they can support. This paper presents the first certified defense that both scales to large networks and datasets (such as Google's Inception network for ImageNet) and applies broadly to arbitrary model types. Our defense, called PixelDP, is based on a novel connection between robustness against adversarial examples and differential privacy, a cryptographically-inspired formalism, that provides a rigorous, generic, and flexible foundation for defense.

In a world where traditional notions of privacy are increasingly challenged by the myriad companies that collect and analyze our data, it is important that decision-making entities are held accountable for unfair treatments arising from irresponsible data usage. Unfortunately, a lack of appropriate methodologies and tools means that even identifying unfair or discriminatory effects can be a challenge in practice. We introduce the unwarranted associations (UA) framework, a principled methodology for the discovery of unfair, discriminatory, or offensive user treatment in data-driven applications. The UA framework unifies and rationalizes a number of prior attempts at formalizing algorithmic fairness. It uniquely combines multiple investigative primitives and fairness metrics with broad applicability, granular exploration of unfair treatment in user subgroups, and incorporation of natural notions of utility that may account for observed disparities. We instantiate the UA framework in FairTest, the first comprehensive tool that helps developers check data-driven applications for unfair user treatment. It enables scalable and statistically rigorous investigation of associations between application outcomes (such as prices or premiums) and sensitive user attributes (such as race or gender). Furthermore, FairTest provides debugging capabilities that let programmers rule out potential confounders for observed unfair effects. We report on use of FairTest to investigate and in some cases address disparate impact, offensive labeling, and uneven rates of algorithmic error in four data-driven applications. As examples, our results reveal subtle biases against older populations in the distribution of error in a predictive health application and offensive racial labeling in an image tagger., Comment: 27 pages, 12 figures