Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given the typically large size of training dataset, manual detection of poisoning is difficult. An alternative is to automatically measure a dataset's robustness against such an attack, which is the focus of this paper. We consider a threat model wherein an adversary can only perturb the labels of the training dataset, with knowledge limited to the hypothesis space of the victim's model. In this setting, we prove that finding the robustness is an NP-Complete problem, even when hypotheses are linear classifiers. To overcome this, we present a technique that finds lower and upper bounds of robustness. Our implementation of the technique computes these bounds efficiently in practice for many publicly available datasets. We experimentally demonstrate the effectiveness of our approach. Specifically, a poisoning exceeding the identified robustness bounds significantly impacts test point classification. We are also able to compute these bounds in many more cases where state-of-the-art techniques fail.

We consider the problem of verification modulo tested library contracts as a step towards automating the verification of client programs that use complex libraries. We formulate this problem as the synthesis of modular contracts for the library methods used by the client that are adequate to prove the client correct, and that also pass the scrutiny of a testing engine that tests the library against these contracts. We also consider a new form of method contracts called contextual contracts that arise in this setting that hold in the context of the client program, and can often be simpler and easier to infer than classical modular contracts. We provide a counterexample-guided learning framework to solve this problem, in which the synthesizer interacts with a constraint solver as well as the testing engine in order to infer adequate modular/contextual method contracts and inductive invariants for the client. The main synthesis engines we use are generalizing CHC solvers that are realized using ICE learning algorithms. We realize this framework in a tool called Dualis and show its efficacy on benchmarks where clients call large libraries.

Abstract Precondition inference is an important problem with many applications in verification and testing. Finding preconditions can be tricky as programs often have loops and arrays, which necessitates finding quantified inductive invariants. However, existing techniques have limitations in finding such invariants, especially when preconditions are missing. Further, maximal (or weakest) preconditions are often required to maximize the usefulness of preconditions. So the inferred inductive invariants have to be adequately weak. To address these challenges, we present an approach for maximal quantified precondition inference using aninfer-check-weakenframework. Preconditions and inductive invariants are inferred by a novel technique calledrange abduction, and then checked for maximality and weakened if required. Range abduction attempts to propagate the given quantified postcondition backwards and then strengthen or weaken it as needed to establish inductiveness. Weakening is done in a syntax-guided fashion. Our evaluation performed on a set of public benchmarks demonstrates that the technique significantly outperforms existing techniques in finding maximal preconditions and inductive invariants.

Abstract Precondition inferenceis an important problem with many applications. Existing precondition inference techniques for programs with arrays have limited ability to find and prove the weakest preconditions, especially when programs have non-determinism. In this paper, we propose an approach to overcome the limitation. As the problem is uncomputable in general, our approach targets a special class of programs called linear array programs that are commonly encountered in practical applications and have been studied before. We also focus on a class of quantified formulas for pre- and postconditions that suffice to specify program properties in many applications. Our approach uses two novel techniques calledStructural Array Abduction(SAA) andSpecialized Maximality Checking(SMC). SAA is an abduction-based technique used to infer quantified preconditions and necessary inductive invariants. SMC proves that an inferred precondition is the weakest by finding an under-approximated program and solving the complement verification problem on it using SAA. When inconclusive, it attempts to weaken the precondition. Our approach can infer (and also prove) the weakest preconditions for a range of benchmarks relatively quickly, and outperforms competing techniques.

The problem of synthesizing specifications of undefined procedures has a broad range of applications, but the usefulness of the generated specifications depends on their quality. In this paper, we propose a technique for finding maximal and non-vacuous specifications. Maximality allows for more choices for implementations of undefined procedures, and non-vacuity ensures that safety assertions are reachable. To handle programs with complex control flow, our technique discovers not only specifications but also inductive invariants. Our iterative algorithm lazily generalizes non-vacuous specifications in a counterexample-guided loop. The key component of our technique is an effective non-vacuous specification synthesis algorithm. We have implemented the approach in a tool called HornSpec, taking as input systems of constrained Horn clauses. We have experimentally demonstrated the tool's effectiveness, efficiency, and the quality of generated specifications on a range of benchmarks.

Programs with arrays are ubiquitous. Automated reasoning about arrays necessitates discovering properties about ranges of elements at certain program points. Such properties are formally specified by universally quantified formulas, which are difficult to find, and difficult to prove inductive. In this paper, we propose an algorithm based on an enumerative search that discovers quantified invariants in stages. First, by exploiting the program syntax, it identifies ranges of elements accessed in each loop. Second, it identifies potentially useful facts about individual elements and generalizes them to hypotheses about entire ranges. Finally, by applying recent advances of SMT solving, the algorithm filters out wrong hypotheses. The combination of properties is often enough to prove that the program meets a safety specification. The algorithm has been implemented in a solver for Constrained Horn Clauses, Freq-Horn, and extended to deal with multiple (possibly nested) loops. We show that FreqHorn advances state-of-the-art on a wide range of public array-handling programs.

A Constrained Horn Clause (CHC) is a logical implication involving unknown predicates. Systems of CHCs are widely used to verify programs with arbitrary loop structures: interpretations of unknown predicates, which make every CHC in the system true, represent the program's inductive invariants. In order to find such solutions, we propose an algorithm based on Syntax-Guided Synthesis. For each unknown predicate, it generates a formal grammar from all relevant parts of the CHC system (i.e., using syntax). Grammars are further enriched by predicates and constants guessed from models of various unrollings of the CHC system (i.e., using data). We propose an iterative approach to guess and check candidates for multiple unknown predicates. At each iteration, only a candidate for one unknown predicate is sampled from its grammar, but then it gets propagated to candidates of the remaining unknowns through implications in the CHC system. Finally, an SMT solver is used to decide if the system of candidates contributes towards a solution or not. We present an evaluation of the algorithm on a range of benchmarks originating from program verification tasks and show that it is competitive with state-of-the-art in CHC solving.