skip to main content

Explore Research Products in the NSF-PAR

  • NSF Public Access
  • Search Results
  • Machine-Checked Proofs for Cryptographic Standards: Indifferentiability of Sponge and Secure High-Assurance Implementations of SHA-3
Title: Machine-Checked Proofs for Cryptographic Standards: Indifferentiability of Sponge and Secure High-Assurance Implementations of SHA-3
We present a high-assurance and high-speed implementation of the SHA-3 hash function. Our implementation is written in the Jasmin programming language, and is formally verified for functional correctness, provable security and timing attack resistance in the EasyCrypt proof assistant. Our implementation is the first to achieve simultaneously the four desirable properties (efficiency, correctness, provable security, and side-channel protection) for a non-trivial cryptographic primitive. Concretely, our mechanized proofs show that: 1) the SHA-3 hash function is indifferentiable from a random oracle, and thus is resistant against collision, first and second preimage attacks; 2) the SHA-3 hash function is correctly implemented by a vectorized x86 implementation. Furthermore, the implementation is provably protected against timing attacks in an idealized model of timing leaks. The proofs include new EasyCrypt libraries of independent interest for programmable random oracles and modular indifferentiability proofs.  more » « less
Award ID(s):
1801564
NSF-PAR ID:
10161927
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ;
Date Published:
Journal Name:
ACM Conference on Computer and Communications Security 2019
Page Range / eLocation ID:
1607 to 1622
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , Lecture notes in computer science)
    null (Ed.)
    The random-permutation model (RPM) and the ideal-cipher model (ICM) are idealized models that offer a simple and intuitive way to assess the conjectured standard-model security of many important symmetric-key and hash-function constructions. Similarly, the generic-group model (GGM) captures generic algorithms against assumptions in cyclic groups by modeling encodings of group elements as random injections and allows to derive simple bounds on the advantage of such algorithms. Unfortunately, both well-known attacks, e.g., based on rainbow tables (Hellman, IEEE Transactions on Information Theory ’80), and more recent ones, e.g., against the discrete-logarithm problem (Corrigan-Gibbs and Kogan, EUROCRYPT ’18), suggest that the concrete security bounds one obtains from such idealized proofs are often completely inaccurate if one considers non-uniform or preprocessing attacks in the standard model. To remedy this situation, this work defines the auxiliary-input (AI) RPM/ICM/GGM, which capture both non-uniform and preprocessing attacks by allowing an attacker to leak an arbitrary (bounded-output) function of the oracle’s function table; derives the first non-uniform bounds for a number of important practical applications in the AI-RPM/ICM, including constructions based on the Merkle-Damgård and sponge paradigms, which underly the SHA hashing standards, and for AI-RPM/ICM applications with computational security; and using simpler proofs, recovers the AI-GGM security bounds obtained by Corrigan-Gibbs and Kogan against preprocessing attackers, for a number of assumptions related to cyclic groups, such as discrete logarithms and Diffie-Hellman problems, and provides new bounds for two assumptions. An important step in obtaining these results is to port the tools used in recent work by Coretti et al. (EUROCRYPT ’18) from the ROM to the RPM/ICM/GGM, resulting in very powerful and easy-to-use tools for proving security bounds against non-uniform and preprocessing attacks. 
    more » « less
  2. ; ; ( , ACM journal on emerging technologies in computing systems)
    We propose AccHashtag, the first framework for high-accuracy detection of fault-injection attacks on Deep Neural Networks (DNNs) with provable bounds on detection performance. Recent literature in fault-injection attacks shows the severe DNN accuracy degradation caused by bit flips. In this scenario, the attacker changes a few DNN weight bits during execution by injecting faults to the dynamic random-access memory (DRAM). To detect bit flips, AccHashtag extracts a unique signature from the benign DNN prior to deployment. The signature is used to validate the model’s integrity and verify the inference output on the fly. We propose a novel sensitivity analysis that identifies the most vulnerable DNN layers to the fault-injection attack. The DNN signature is constructed by encoding the weights in vulnerable layers using a low-collision hash function. During DNN inference, new hashes are extracted from the target layers and compared against the ground-truth signatures. AccHashtag incorporates a lightweight methodology that allows for real-time fault detection on embedded platforms. We devise a specialized compute core for AccHashtag on field-programmable gate arrays (FPGAs) to facilitate online hash generation in parallel to DNN execution. Extensive evaluations with the state-of-the-art bit-flip attack on various DNNs demonstrate the competitive advantage of AccHashtag in terms of both attack detection and execution overhead. 
    more » « less
  3. ; ; ; ( , SOSP '17 Proceedings of the 26th Symposium on Operating Systems Principles)
    Intel SGX promises powerful security: an arbitrary number of user-mode enclaves protected against physical attacks and privileged software adversaries. However, to achieve this, Intel extended the x86 architecture with an isolation mechanism approaching the complexity of an OS microkernel, implemented by an inscrutable mix of silicon and microcode. While hardware-based security can offer performance and features that are difficult or impossible to achieve in pure software, hardware-only solutions are difficult to update, either to patch security flaws or introduce new features. Komodo illustrates an alternative approach to attested, on-demand, user-mode, concurrent isolated execution. We decouple the core hardware mechanisms such as memory encryption, address-space isolation and attestation from the management thereof, which Komodo delegates to a privileged software monitor that in turn implements enclaves. The monitor's correctness is ensured by a machine-checkable proof of both functional correctness and high-level security properties of enclave integrity and confidentiality. We show that the approach is practical and performant with a concrete implementation of a prototype in verified assembly code on ARM TrustZone. Our ultimate goal is to achieve security equivalent to or better than SGX while enabling deployment of new enclave features independently of CPU upgrades. The Komodo specification, prototype implementation, and proofs are available at https://github.com/Microsoft/Komodo. 
    more » « less
  4. ; ; ; ; ( , Innovations in Theoretical Computer Science Conference)
    In a key-agreement protocol whose security is proven in the random oracle model (ROM), the parties and the eavesdropper can make bounded number of queries to a shared random function (an “oracle”). Such protocol are the alternative to key-agreement protocols whose security is based on “public-key assumptions”, assumptions that being more structured are presumingly more vulnerable to attacks. Barak and Mahmoody [Crypto ’09] (following Impagliazzo and Rudich [STOC ’89]) have shown the ROM key-agreement protocols can only guarantee limited secrecy: the key of any `l-query protocol can be revealed by an O(l^2 )-query adversary, a bound that matches the gap obtained by the Merkle’s Puzzles two-message protocol of Merkle [CACM ’78]. While this quadratic gap might not seem like much, if the honest parties are willing to work “hard enough” and given continuousness improvement in common hash functions evaluation time, this gap yields a good enough advantage (assuming the security of the protocol holds when initiating the random function with a fixed hash function). In this work we consider the communication complexity of ROM key-agreement protocols. In Merkle’s Puzzles, the honest parties need to exchange Ω(l) bits (ignoring logarithmic factors) to obtain secrecy against an eavesdropper that makes roughly l^2 queries, which makes the protocol unrealizable in many settings. We show that for protocols with certain natural properties, such high communication is unavoidable. Specifically, this is the case if the honest parties’ queries are independent and uniformly random, or alternatively if the protocol uses non-adaptive queries and has only two rounds. Since two-round key-agreement protocol are equivalent to public-key encryption scheme (seeing the first message as the public-key), the latter result bounds the public-key and encryption size of public-key encryption scheme whose security is proven in the ROM. 
    more » « less
  5. ; ; ( , CCS '17 Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security)
    The MD transform that underlies the MD and SHA families iterates a compression function h to get a hash function H. The question we ask is, what property X of h guarantees collision resistance (CR) of H? The classical answer is that X itself be CR. We show that weaker conditions X, in particular forms of what we call constrained-CR, suffice. This reduces demands on compression functions, to the benefit of security, and also, forensically, explains why collision-finding attacks on compression functions have not, historically, lead to immediate breaks of the corresponding hash functions. We obtain our results via a definitional framework called RS security, and a parameterized treatment of MD, that also serve to unify prior work and variants of the transform. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email