Establishing quantitative bounds on the execution cost of programs is essential in many areas of computer science such as complexity analysis, compiler optimizations, security and privacy. Techniques based on program analysis, type systems and abstract interpretation are well-studied, but methods for analyzing how the execution costs of two programs compare to each other have not received attention. Naively combining the worst and best case execution costs of the two programs does not work well in many cases because such analysis forgets the similarities between the programs or the inputs. In this work, we propose a relational cost analysis technique that is capable of establishing precise bounds on the difference in the execution cost of two programs by making use of relational properties of programs and inputs. We develop RelCost, a refinement type and effect system for a higher-order functional language with recursion and subtyping. The key novelty of our technique is the combination of relational refinements with two modes of typing-relational typing for reasoning about similar computations/inputs and unary typing for reasoning about unrelated computations/inputs. This combination allows us to analyze the execution cost difference of two programs more precisely than a naive non-relational approach. We prove our type system sound using a semantic model based on step-indexed unary and binary logical relations accounting for non-relational and relational reasoning principles with their respective costs. We demonstrate the precision and generality of our technique through examples.

Abstract. We show that the call-by-name monad translation of simply typed lambda calculus extended with sum and product types extends to special and general inductive and coinductive types so that its crucial property of preserving typings and β-and commuting reductions is maintained. Specific similar-purpose translations such as CPS translations follow from the general monad translations by specialization for appropriate concrete monads.

We study decidability problems for equivalence of probabilistic programs for a core probabilistic programming language over finite fields of fixed characteristic. The programming language supports uniform sampling, addition, multiplication, and conditionals and thus is sufficiently expressive to encode Boolean and arithmetic circuits. We consider two variants of equivalence: The first one considers an interpretation over the finite field F q , while the second one, which we call universal equivalence, verifies equivalence over all extensions F q k of F q . The universal variant typically arises in provable cryptography when one wishes to prove equivalence for any length of bitstrings, i.e., elements of F 2 k for any k . While the first problem is obviously decidable, we establish its exact complexity, which lies in the counting hierarchy. To show decidability and a doubly exponential upper bound of the universal variant, we rely on results from algorithmic number theory and the possibility to compare local zeta functions associated to given polynomials. We then devise a general way to draw links between the universal probabilistic problems and widely studied problems on linear recurrence sequences. Finally, we study several variants of the equivalence problem, including a problem we call majority, motivated by differential privacy. We also define and provide some insights about program indistinguishability, proving that it is decidable for programs always returning 0 or 1.

Relational program logics have been used for mechanizing formal proofs of various cryptographic constructions. With an eye towards scaling these successes towards end-to-end security proofs for implementations of distributed systems, we present RF*, a relational extension of F*, a general-purpose higher-order stateful programming language with a verification system based on refinement types. The distinguishing feature of F* is a relational Hoare logic for a higher-order, stateful, probabilistic language. Through careful language design, we adapt the F* typechecker to generate both classic and relational verification conditions, and to automatically discharge their proofs using an SMT solver. Thus, we are able to benefit from the existing features of F*, including its abstraction facilities for modular reasoning about program fragments. We evaluate RF* experimentally by programming a series of cryptographic constructions and protocols, and by verifying their security properties, ranging from information flow to unlinkability, integrity, and privacy. Moreover, we validate the design of RF* by formalizing in Coq a core probabilistic λ calculus and a relational refinement type system and proving the soundness of the latter against a denotational semantics of the probabilistic lambda λ calculus.