Chao Wang

Chao Wang

Auto-generated profile, based on publicly available information

Chao Wang

University of Southern California

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 September 2017 in Formal Methods in System Design
Verified
Journal Article
Open access
PDF file
BKBettina Könighofer
Bettina Könighofer
MAMohammed Alshiekh
Mohammed Alshiekh
RBRoderick Bloem
Roderick Bloem
LHLaura Humphrey
Laura Humphrey
RKRobert Könighofer
Robert Könighofer
CWChao Wang
Chao Wang
Shield synthesis is an approach to enforce safety properties at runtime. A shield monitors the system and corrects any erroneous output values instantaneously. The shield deviates from the given outputs as little as it can and recovers to hand back control to the system as soon as possible. In the first part of this paper, we consider shield synthesis for reactive hardware systems. First, we define a general framework for solving the shield synthesis problem. Second, we discuss two concrete shield synthesis methods that automatically construct shields from a set of safety properties: (1) k-stabilizing shields, which guarantee recovery in a finite time. (2) Admissible shields, which attempt to work with the system to recover as soon as possible. Next, we discuss an extension of k-stabilizing and admissible shields, where erroneous output values of the reactive system are corrected while liveness properties of the system are preserved. Finally, we give experimental results for both synthesis methods. In the second part of the paper, we consider shielding a human operator instead of shielding a reactive system: the outputs to be corrected are not initiated by a system but by a human operator who works with an autonomous system. The challenge here lies in giving simple and intuitive explanations to the human for any interferences of the shield. We present results involving mission planning for unmanned aerial vehicles.

30 March 2022
Verified
Book Chapter
Open access
PDF file
BPBrandon Paulsen
Brandon Paulsen
CWChao Wang
Chao Wang
The most scalable approaches to certifying neural network robustness depend on computing sound linear lower and upper bounds for the network’s activation functions. Current approaches are limited in that the linear bounds must be handcrafted by an expert, and can be sub-optimal, especially when the network’s architecture composes operations using, for example, multiplication such as in LSTMs and the recently popularSwishactivation. The dependence on an expert prevents the application of robustness certification to developments in the state-of-the-art of activation functions, and furthermore the lack of tightness guarantees may give a false sense of insecurity about a particular model. To the best of our knowledge, we are the first to consider the problem ofautomaticallysynthesizingtightlinear bounds for arbitrary n-dimensional activation functions. We propose the first fully automated method that achieves tight linear bounds while only leveraging the mathematical definition of the activation function itself. Our method leverages an efficient heuristic technique to synthesize bounds that are tight andusually sound, and then verifies the soundness (and adjusts the bounds if necessary) using the highly optimized branch-and-bound SMT solver,dReal. Even though our method depends on an SMT solver, we show that the runtime is reasonable in practice, and, compared with state of the art, our method often achieves 2-5X tighter final output bounds and more than quadruple certified robustness.

7 August 2022
Verified
Book Chapter
Open access
PDF file
BPBrandon Paulsen
Brandon Paulsen
CWChao Wang
Chao Wang
Linear approximations of nonlinear functions have a wide range of applications such as rigorous global optimization and, recently, verification problems involving neural networks. In the latter case, a linear approximation must be hand-crafted for the neural network’s activation functions. This hand-crafting is tedious, potentially error-prone, and requires an expert to prove the soundness of the linear approximation. Such a limitation is at odds with the rapidly advancing deep learning field – current verification tools either lack the necessary linear approximation, or perform poorly on neural networks with state-of-the-art activation functions. In this work, we consider the problem of automatically synthesizing sound linear approximations for a given neural network activation function. Our approach is example-guided: we develop a procedure to generate examples, and then we leverage machine learning techniques to learn a (static) function that outputs linear approximations. However, since the machine learning techniques we employ do not come with formal guarantees, the resulting synthesized function may produce linear approximations with violations. To remedy this, we bound the maximum violation using rigorous global optimization techniques, and then adjust the synthesized linear approximation accordingly to ensure soundness. We evaluate our approach on several neural network verification tasks. Our evaluation shows that the automatically synthesized linear approximations greatly improve the accuracy (i.e., in terms of the number of verification problems solved) compared to hand-crafted linear approximations in state-of-the-art neural network verification tools. An artifact with our code and experimental scripts is available at: https://zenodo.org/record/6525186#.Yp51L9LMIzM. "Image missing""Image missing"

18 July 2023
Verified
Book Chapter
Open access
PDF file
YLYannan Li
Yannan Li
JWJingbo Wang
Jingbo Wang
CWChao Wang
Chao Wang
We propose a method for certifying the fairness of the classification result of a widely used supervised learning algorithm, thek-nearest neighbors (KNN), under the assumption that the training data may have historical bias caused by systematic mislabeling of samples from a protected minority group. To the best of our knowledge, this is the first certification method for KNN based on three variants of the fairness definition: individual fairness, $$\epsilon $$ -fairness, and label-flipping fairness. We first define the fairness certification problem for KNN and then propose sound approximations of the complex arithmetic computations used in the state-of-the-art KNN algorithm. This is meant to lift the computation results from the concrete domain to an abstract domain, to reduce the computational cost. We show effectiveness of thisabstract interpretationbased technique through experimental evaluation on six datasets widely used in the fairness research literature. We also show that the method is accurate enough to obtain fairness certifications for a large number of test inputs, despite the presence of historical bias in the datasets.

31 July 2018 in IEEE Transactions on Software Engineering
Verified
Journal Article
Closed access
TYTingting Yu
Tingting Yu
ZHZunchen Huang
Zunchen Huang
CWChao Wang
Chao Wang
As software evolves, test suite augmentation techniques may be used to identify which part of the program needs to be tested due to code changes and how to generate these new test cases for regression testing. However, existing techniques focus exclusively on sequential software, without considering concurrent software in which multiple threads may interleave with each other during the execution and thus lead to a combinatorial explosion. To fill the gap, we propose ConTesa , the first test suite augmentation tool for concurrent software. The goal is to generate new test cases capable of exercising both code changes and the thread interleavings affected by these code changes. At the center of ConTesa is a two-pronged approach. First, it judiciously reuses the current test inputs while amplifying their interleaving coverage using random thread schedules. Then, it leverages an incremental symbolic execution technique to generate more test inputs and interleavings, to cover the new concurrency-related program behaviors. We have implemented ConTesa and evaluated it on a set of real-world multithreaded Linux applications. Our results show that it can achieve a significantly high interleaving coverage and reveal more bugs than state-of-the-art testing techniques.

12 April 2024
Verified
Conference Paper
Open access
ZHZunchen Huang
Zunchen Huang
CWChao Wang
Chao Wang
We propose a constraint based method for repairing bugs associated with the use of persistent memory (PM) in application software. Our method takes a program execution trace and the violated property as input and returns a suggested repair, which is a combination of inserting new PM instructions and reordering these instructions to eliminate the property violation. Compared with the state-of-the-art approach, our method has three advantages. First, it can repair both durability and crash consistency bugs whereas the state-of-the-art approach can only repair the relatively-simple durability bugs. Second, our method can discover new repair strategies instead of relying on repair strategies hard-coded into the repair tool. Third, our method uses a novel symbolic encoding to model PM semantics, which allows our symbolic analysis to be more efficient than the explicit enumeration of possible scenarios and thus explore a large number of repairs quickly. We have evaluated our method on benchmark programs from the well-known Intel PMDK library as well as real applications such as Memcached, Recipe, and Redis. The results show that our method can repair all of the 41 known bugs in these benchmarks, while the state-of-the-art approach cannot repair any of the crash consistency bugs.