Symbolic execution is a powerful technique that can generate tests steering program execution into desired paths. However, the scalability of symbolic execution is often limited by path explosion, i.e., the number of symbolic states representing the paths under exploration quickly explodes as execution goes on. Therefore, the effectiveness of symbolic execution engines hinges on the ability to select and explore the right symbolic states.

Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense’s inner workings, or to approaches based on ensemble of fixed attacks, none of which may be effective for the specific defense at hand. Our key observation is that adaptive attacks are composed from a set of reusable building blocks that can be formalized in a search space and used to automatically discover attacks for unknown defenses. We evaluated our approach on 24 adversarial defenses and show that it outperforms AutoAttack, the current state-of-the-art tool for reliable evaluation of adversarial defenses: our tool discovered significantly stronger attacks by producing 3.0%-50.8% additional adversarial examples for 10 models, while obtaining attacks with slightly stronger or similar strength for the remaining models.

Not all important network properties need to be enforced all the time. Often, what matters instead is the fraction of time / probability these properties hold. Computing the probability of a property in a network relying on complex inter-dependent routing protocols is challenging and requires determining all failure scenarios for which the property is violated. Doing so at scale and accurately goes beyond the capabilities of current network analyzers.

We present VerX, the first automated verifier able to prove functional properties of Ethereum smart contracts. VerX addresses an important problem as all real-world contracts must satisfy custom functional specifications.VerX is based on a careful combination of three techniques, enabling it to automatically verify temporal properties of infinite- state smart contracts: (i) reduction of temporal property verification to reachability checking, (ii) a new symbolic execution engine for the Ethereum Virtual Machine that is precise and efficient for a practical fragment of Ethereum contracts, and (iii) delayed predicate abstraction which uses symbolic execution during transactions and abstraction at transaction boundaries.Our extensive experimental evaluation on 83 temporal properties and 12 real-world projects, including popular crowdsales and libraries, demonstrates that VerX is practically effective.

Fuzzing and symbolic execution are two complementary techniques for discovering software vulnerabilities. Fuzzing is fast and scalable, but can be ineffective when it fails to randomly select the right inputs. Symbolic execution is thorough but slow and often does not scale to deep program paths with complex path conditions. In this work, we propose to learn an effective and fast fuzzer from symbolic execution, by phrasing the learning task in the framework of imitation learning. During learning, a symbolic execution expert generates a large number of quality inputs improving coverage on thousands of programs. Then, a fuzzing policy, represented with a suitable architecture of neural networks, is trained on the generated dataset. The learned policy can then be used to fuzz new programs. We instantiate our approach to the problem of fuzzing smart contracts, a domain where contracts often implement similar functionality (facilitating learning) and security is of utmost importance. We present an end-to-end system, ILF (for Imitation Learning based Fuzzer), and an extensive evaluation over >18K contracts. Our results show that ILF is effective: (i) it is fast, generating 148 transactions per second, (ii) it outperforms existing fuzzers (e.g., achieving 33% more coverage), and (iii) it detects more vulnerabilities than existing fuzzing and symbolic execution tools for Ethereum.

Privacy concerns of smart contracts are a major roadblock preventing their wider adoption. A promising approach to protect private data is hiding it with cryptographic primitives and then enforcing correctness of state updates by Non-Interactive Zero-Knowledge (NIZK) proofs. Unfortunately, NIZK statements are less expressive than smart contracts, forcing developers to keep some functionality in the contract. This results in scattered logic, split across contract code and NIZK statements, with unclear privacy guarantees. To address these problems, we present the zkay language, which introduces privacy types defining owners of private values. zkay contracts are statically type checked to (i) ensure they are realizable using NIZK proofs and (ii) prevent unintended information leaks. Moreover, the logic of zkay contracts is easy to follow by just ignoring privacy types. To enforce zkay contracts, we automatically transform them into contracts equivalent in terms of privacy and functionality, yet executable on public blockchains. We evaluated our approach on a proof-of-concept implementation generating Solidity contracts and implemented 10 interesting example contracts in zkay. Our results indicate that zkay is practical: On-chain cost for executing the transformed contracts is around 1M gas per transaction (~0.50US$) and off-chain cost is moderate.

We present DP-Finder, a novel approach and system that automatically derives lower bounds on the differential privacy enforced by algorithms. Lower bounds are practically useful as they can show tightness of existing upper bounds or even identify incorrect upper bounds. Computing a lower bound involves searching for a counterexample, defined by two neighboring inputs and a set of outputs, that identifies a large privacy violation. This is an inherently hard problem as finding such a counterexample involves inspecting a large (usually infinite) and sparse search space. To address this challenge, DP-Finder relies on two key insights. First, we introduce an effective and precise correlated sampling method to estimate the privacy violation of a counterexample. Second, we show how to obtain a differentiable version of the problem, enabling us to phrase the search task as an optimization objective to be maximized with state-of-the-art numerical optimizers. This allows us to systematically search for large privacy violations. Our experimental results indicate that DP-Finder is effective in computing differential privacy lower bounds for a number of randomized algorithms. For instance, it finds tight lower bounds in algorithms that obfuscate their input in a non-trivial fashion.

We present a novel approach for predicting debug information in stripped binaries. Using machine learning, we first train probabilistic models on thousands of non-stripped binaries and then use these models to predict properties of meaningful elements in unseen stripped binaries. Our focus is on recovering symbol names, types and locations, which are critical source-level information wiped off during compilation and stripping. Our learning approach is able to distinguish and extract key elements such as register-allocated and memory-allocated variables usually not evident in the stripped binary. To predict names and types of extracted elements, we use scalable structured prediction algorithms in probabilistic graphical models with an extensive set of features which capture key characteristics of binary code. Based on this approach, we implemented an automated tool, called Debin, which handles ELF binaries on three of the most popular architectures: x86, x64 and ARM. Given a stripped binary, Debin outputs a binary augmented with the predicted debug information. Our experimental results indicate that Debin is practically useful: for x64, it predicts symbol names and types with 68.8% precision and 68.3% recall. We also show that Debin is helpful for the task of inspecting real-world malware -- it revealed suspicious library usage and behaviors such as DNS resolver reader.

Permissionless blockchains allow the execution of arbitrary programs (called smart contracts), enabling mutually untrusted entities to interact without relying on trusted third parties. Despite their potential, repeated security concerns have shaken the trust in handling billions of USD by smart contracts. To address this problem, we present Securify, a security analyzer for Ethereum smart contracts that is scalable, fully automated, and able to prove contract behaviors as safe/unsafe with respect to a given property. Securify's analysis consists of two steps. First, it symbolically analyzes the contract's dependency graph to extract precise semantic information from the code. Then, it checks compliance and violation patterns that capture sufficient conditions for proving if a property holds or not. To enable extensibility, all patterns are specified in a designated domain-specific language. Securify is publicly released, it has analyzed >18K contracts submitted by its users, and is regularly used to conduct security audits by experts. We present an extensive evaluation of Securify over real-world Ethereum smart contracts and demonstrate that it can effectively prove the correctness of smart contracts and discover critical violations.

Network operators often need to ensure that important probabilistic properties are met, such as that the probability of network congestion is below a certain threshold. Ensuring such properties is challenging and requires both a suitable language for probabilistic networks and an automated procedure for answering probabilistic inference queries.

Creating and maintaining an up-to-date set of security rules that match misuses of crypto APIs is challenging, as crypto APIs constantly evolve over time with new cryptographic primitives and settings, making existing ones obsolete.

We present AI2, the first sound and scalable analyzer for deep neural networks. Based on overapproximation, AI2can automatically prove safety properties (e.g., robustness) of realistic neural networks (e.g., convolutional neural networks). The key insight behind AI2is to phrase reasoning about safety and robustness of neural networks in terms of classic abstract interpretation, enabling us to leverage decades of advances in that area. Concretely, we introduce abstract transformers that capture the behavior of fully connected and convolutional neural network layers with rectified linear unit activations (ReLU), as well as max pooling layers. This allows us to handle real-world neural networks, which are often built out of those types of layers. We present a complete implementation of AI2together with an extensive evaluation on 20 neural networks. Our results demonstrate that: (i) AI2is precise enough to prove useful specifications (e.g., robustness), (ii) AI2can be used to certify the effectiveness of state-of-the-art defenses for neural networks, (iii) AI2is significantly faster than existing analyzers based on symbolic analysis, which often take hours to verify simple fully connected networks, and (iv) AI2can handle deep convolutional networks, which are beyond the reach of existing methods.

Existing probabilistic privacy enforcement approaches permit the execution of a program that processes sensitive data only if the information it leaks is within the bounds specified by a given policy. Thus, to extract any information, users must manually design a program that satisfies the policy. In this work, we present a novel synthesis approach that automatically transforms a program into one that complies with a given policy. Our approach consists of two ingredients. First, we phrase the problem of determining the amount of leaked information as Bayesian inference, which enables us to leverage existing probabilistic programming engines. Second, we present two synthesis procedures that add uncertainty to the program's outputs as a way of reducing the amount of leaked information: an optimal one based on SMT solving and a greedy one with quadratic running time. We implemented and evaluated our approach on 10 representative programs from multiple application domains. We show that our system can successfully synthesize a permissive enforcement mechanism for all examples.

Test isolation is a prerequisite for the correct execution of test suites on web applications. We present Test Execution Checkpointing, a method for efficient test isolation. Our method instruments web applications to support checkpointing and exploits this support to isolate and optimize tests. We have implemented and evaluated this method on five popular PHP web applications. The results show that our method not only provides test isolation essentially for free, it also reduces testing time by 44% on average.

This work presents a new approach for deobfuscating Android APKs based on probabilistic learning of large code bases (termed "Big Code"). The key idea is to learn a probabilistic model over thousands of non-obfuscated Android applications and to use this probabilistic model to deobfuscate new, unseen Android APKs. The concrete focus of the paper is on reversing layout obfuscation, a popular transformation which renames key program elements such as classes, packages, and methods, thus making it difficult to understand what the program does. Concretely, the paper: (i) phrases the layout deobfuscation problem of Android APKs as structured prediction in a probabilistic graphical model, (ii) instantiates this model with a rich set of features and constraints that capture the Android setting, ensuring both semantic equivalence and high prediction accuracy, and (iii) shows how to leverage powerful inference and learning algorithms to achieve overall precision and scalability of the probabilistic predictions.

Access-control requirements for physical spaces, like office buildings and airports, are best formulated from a global viewpoint in terms of system-wide requirements. For example, "there is an authorized path to exit the building from every room." In contrast, individual access-control components, such as doors and turnstiles, can only enforce local policies, specifying when the component may open. In practice, the gap between the system-wide, global requirements and the many local policies is bridged manually, which is tedious, error-prone, and scales poorly. We propose a framework to automatically synthesize local access control policies from a set of global requirements for physical spaces. Our framework consists of an expressive language to specify both global requirements and physical spaces, and an algorithm for synthesizing local, attribute-based policies from the global specification. We empirically demonstrate the framework's effectiveness on three substantial case studies. The studies demonstrate that access control synthesis is practical even for complex physical spaces, such as airports, with many interrelated security requirements.

Decentralized and distributed access control systems are subject to communication and component failures. These can affect access decisions in surprising and unintended ways, resulting in insecure systems. Existing analysis frameworks however ignore the influence of failure handling in decision making. Thus, it is currently all but impossible to derive security guarantees for systems that may fail. To address this, we present (1) a model in which the attacker can explicitly induce failures, (2) failure-handling idioms, and (3) a method and an associated tool for verifying fail-security requirements, which describe how access control systems should handle failures. To illustrate these contributions, we analyze the consequences of failure handling in the XACML 3 standard and other domains, revealing security flaws.

We define semi-valid input coverage (SVCov), the first coverage criterion for fuzz testing. Our criterion is applicable whenever the valid inputs can be defined by a finite set of constraints. SVCov measures to what extent the tests cover the domain of semi-valid inputs, where an input is semi-valid if and only if it satisfies all the constraints but one.

Typically, dynamic-analysis techniques operate on a small subset of all possible program behaviors, which limits their effectiveness and the representativeness of the computed results. To address this issue, a new paradigm is emerging: execution hijacking, consisting of techniques that explore a larger set of program behaviors by forcing executions along specific paths. Although hijacked executions are infeasible for the given inputs, they can still produce feasible behaviors that could be observed under other inputs. In such cases, execution hijacking can improve the effectiveness of dynamic analysis without requiring the (expensive) generation of additional inputs. To evaluate the usefulness of execution hijacking, we defined, implemented, and evaluated several variants of it. Specifically, we performed an empirical study where we assessed whether execution hijacking could improve the effectiveness of a common dynamic analysis: memory error detection. The results of the study show that execution hijacking, if suitably performed, can indeed improve dynamic analysis.