Detecting harmful data races through parallel verification

Wu, Zhendong; Lü, Kai; Wang, Xiaoping; Zhou, Xu; Chen, Chen

doi:10.1007/s11227-015-1418-8

Cited by 13 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future works on this topic may include mining deeper into the source data. Firstly, we can match accounts using some kind of correlational analysis [39][40][41][42][43] instead of simply using email addresses. Secondly, other TarGuess models [7], which utilize PII info, can also be used to improve the result of the proposed guessing algorithm.…”

Section: Impact Of Global Rankingmentioning

confidence: 99%

Study on Massive-Scale Slow-Hash Recovery Using Unified Probabilistic Context-Free Grammar and Symmetrical Collaborative Prioritization with Parallel Machines

Yang

Wang³

et al. 2019

Symmetry

View full text Add to dashboard Cite

Slow-hash algorithms are proposed to defend against traditional offline password recovery by making the hash function very slow to compute. In this paper, we study the problem of slow-hash recovery on a large scale. We attack the problem by proposing a novel concurrent model that guesses the target password hash by leveraging known passwords from a largest-ever password corpus. Previously proposed password-reused learning models are specifically designed for targeted online guessing for a single hash and thus cannot be efficiently parallelized for massive-scale offline recovery, which is demanded by modern hash-cracking tasks. In particular, because the size of a probabilistic context-free grammar (PCFG for short) model is non-trivial and keeping track of the next most probable password to guess across all global accounts is difficult, we choose clever data structures and only expand transformations as needed to make the attack computationally tractable. Our adoption of max-min heap, which globally ranks weak accounts for both expanding and guessing according to unified PCFGs and allows for concurrent global ranking, significantly increases the hashes can be recovered within limited time. For example, 59.1% accounts in one of our target password list can be found in our source corpus, allowing our solution to recover 20.1% accounts within one week at an average speed of 7200 non-identical passwords cracked per hour, compared to previous solutions such as oclHashcat (using default configuration), which cracks at an average speed of 28 and needs months to recover the same number of accounts with equal computing resources (thus are infeasible for a real-world attacker who would maximize the gain against the cracking cost). This implies an underestimated threat to slow-hash protected password dumps. Our method provides organizations with a better model of offline attackers and helps them better decide the hashing costs of slow-hash algorithms and detect potential vulnerable credentials before hackers do.

show abstract

Section: Impact Of Global Rankingmentioning

confidence: 99%

Study on Massive-Scale Slow-Hash Recovery Using Unified Probabilistic Context-Free Grammar and Symmetrical Collaborative Prioritization with Parallel Machines

Yang

Wang³

et al. 2019

Symmetry

View full text Add to dashboard Cite

show abstract

“…In order to reduce the total verification time, we use pre-execution to help divide the potential race [12]. For example, if we need to allocate the multi-thread program FFT to two servers, we first perform FFT on both servers and record the execution time of the FFT on each server.…”

Section: Dividing Racesmentioning

confidence: 99%

“…Multiple potential races in one group can be verified in one execution. Although those detectors identify the harmful races automatically [12], they still suffer from several limitations on efficiency. This greatly affects the software testing process.…”

Section: Introductionmentioning

confidence: 99%

A Concurrent Harmful Races Identification Algorithm using Hadoop and Multiple Cloud Servers

Suxia¹

2018

IJPE

View full text Add to dashboard Cite

Data race is widespread in multi-thread programs and can lead to serious failures. To improve the reliability of programs, many race detectors have been proposed. However, most of the detectors use binary instrumentation to detect potential races, imposing higher runtime overhead. Most of the potential races are false positive, which consumes manual effort to identify the harmful races. In order to reduce runtime overhead of identifying harmful races, we propose two concurrent strategies that reduce runtime overhead from the detection potential races stage and the verification harmful races stage. Unlike previous work, the detection and verification races are in one execution. In this paper, the Hadoop distributed system is used to detect the potential races concurrently from the trace, and then the weighted Round-Robin algorithm is used to divide all potential races to multiple cloud servers. Harmful races are verified concurrently in multiple cloud servers by controlling thread scheduling. The experimental results show that our method for identifying harmful races is more efficient. Compared with RaceFuzzer and ReceChecker, the runtime overhead is reduced by an average of 72% and 46% respectively. In addition, a good speedup is achieved in this paper.

show abstract

“…Simply put, if one operation modifies data, the data are read by another operation, and the first operation happens-before the second operation, the second operation is guaranteed to see the changes made by the first operation. Having such model is essential for B Jiri Dokulil jiri.dokulil@univie.ac.at 1 Faculty of Computer Science, University of Vienna, Vienna, Austria programmers' understanding of the code, but it can also be used in tools that detect errors such as data races [20,22].…”

Section: Introductionmentioning

confidence: 99%

Consistency model for runtime objects in the Open Community Runtime

Dokulil

2018

J Supercomput

View full text Add to dashboard Cite

Task-based runtime systems are seen as a way to deal with increasing heterogeneity and performance variability in modern high performance computing systems. The Open Community Runtime is an example of such runtime system, with the benefit of having an open specification that defines its interface and behavior. This allows others to study the design and create alternative implementations of the runtime system. However, it turns out that the consistency model that defines how the OCR programs are synchronized when executed in parallel is not sufficiently defined. In the following text, we complete the consistency model by filling in the missing pieces and extending the memory model given in the specification.

show abstract

Detecting harmful data races through parallel verification

Cited by 13 publications

References 28 publications

Study on Massive-Scale Slow-Hash Recovery Using Unified Probabilistic Context-Free Grammar and Symmetrical Collaborative Prioritization with Parallel Machines

Study on Massive-Scale Slow-Hash Recovery Using Unified Probabilistic Context-Free Grammar and Symmetrical Collaborative Prioritization with Parallel Machines

A Concurrent Harmful Races Identification Algorithm using Hadoop and Multiple Cloud Servers

Consistency model for runtime objects in the Open Community Runtime

Contact Info

Product

Resources

About