Matches in SemOpenAlex for { <https://semopenalex.org/work/W2955544047> ?p ?o ?g. }
- W2955544047 abstract "The growing security threat of microarchitectural attacks underlines the importance of robust security sensors and detection mechanisms at the hardware level. While there are studies on runtime detection of cache attacks, a generic model to consider the broad range of existing and future attacks is missing. Unfortunately, previous approaches only consider either a single attack variant, e.g. Prime+Probe, or specific victim applications such as cryptographic implementations. Furthermore, the state-of-the art anomaly detection methods are based on coarse-grained statistical models, which are not successful to detect anomalies in a large-scale real world systems. Thanks to the memory capability of advanced Recurrent Neural Networks (RNNs) algorithms, both short and long term dependencies can be learned more accurately. Therefore, we propose FortuneTeller, which for the first time leverages the superiority of RNNs to learn complex execution patterns and detects unseen microarchitectural attacks in real world systems. FortuneTeller models benign workload pattern from a microarchitectural standpoint in an unsupervised fashion, and then, it predicts how upcoming benign executions are supposed to behave. Potential attacks and malicious behaviors will be detected automatically, when there is a discrepancy between the predicted execution pattern and the runtime observation. We implement FortuneTeller based on the available hardware performance counters on Intel processors and it is trained with 10 million samples obtained from benign applications. For the first time, the latest attacks such as Meltdown, Spectre, Rowhammer and Zombieload are detected with one trained model and without observing these attacks during the training. We show that FortuneTeller achieves F-score of 0.9970." @default.
- W2955544047 created "2019-07-12" @default.
- W2955544047 creator A5027999421 @default.
- W2955544047 creator A5060182940 @default.
- W2955544047 creator A5066592325 @default.
- W2955544047 creator A5075079896 @default.
- W2955544047 date "2019-07-08" @default.
- W2955544047 modified "2023-10-01" @default.
- W2955544047 title "FortuneTeller: Predicting Microarchitectural Attacks via Unsupervised Deep Learning" @default.
- W2955544047 cites W1412775481 @default.
- W2955544047 cites W1427174644 @default.
- W2955544047 cites W1499864241 @default.
- W2955544047 cites W1503814339 @default.
- W2955544047 cites W1545528966 @default.
- W2955544047 cites W1664413462 @default.
- W2955544047 cites W1964241047 @default.
- W2955544047 cites W1992291252 @default.
- W2955544047 cites W2007388836 @default.
- W2955544047 cites W2061354941 @default.
- W2955544047 cites W2071289869 @default.
- W2955544047 cites W2087300543 @default.
- W2955544047 cites W2088503757 @default.
- W2955544047 cites W2101778912 @default.
- W2955544047 cites W2103289002 @default.
- W2955544047 cites W2132350687 @default.
- W2955544047 cites W2163563130 @default.
- W2955544047 cites W2166844173 @default.
- W2955544047 cites W2171929398 @default.
- W2955544047 cites W2228696070 @default.
- W2955544047 cites W2255548496 @default.
- W2955544047 cites W2296391043 @default.
- W2955544047 cites W2296602564 @default.
- W2955544047 cites W2315350509 @default.
- W2955544047 cites W2329308213 @default.
- W2955544047 cites W2337480911 @default.
- W2955544047 cites W2402144811 @default.
- W2955544047 cites W2402268235 @default.
- W2955544047 cites W2463456957 @default.
- W2955544047 cites W2484027757 @default.
- W2955544047 cites W2507765405 @default.
- W2955544047 cites W2522718524 @default.
- W2955544047 cites W2529582363 @default.
- W2955544047 cites W2532499458 @default.
- W2955544047 cites W2564856904 @default.
- W2955544047 cites W2585270215 @default.
- W2955544047 cites W2586555532 @default.
- W2955544047 cites W2664885055 @default.
- W2955544047 cites W2739032812 @default.
- W2955544047 cites W2767094836 @default.
- W2955544047 cites W2770572532 @default.
- W2955544047 cites W2788636062 @default.
- W2955544047 cites W2792326895 @default.
- W2955544047 cites W2803900647 @default.
- W2955544047 cites W2807403537 @default.
- W2955544047 cites W2883613460 @default.
- W2955544047 cites W2888798936 @default.
- W2955544047 cites W2889434695 @default.
- W2955544047 cites W2902762277 @default.
- W2955544047 cites W2945838820 @default.
- W2955544047 cites W2948017961 @default.
- W2955544047 cites W2949190449 @default.
- W2955544047 cites W2949317607 @default.
- W2955544047 cites W2950774332 @default.
- W2955544047 cites W2954241526 @default.
- W2955544047 cites W2962824709 @default.
- W2955544047 cites W2964206587 @default.
- W2955544047 cites W98341770 @default.
- W2955544047 cites W2113261561 @default.
- W2955544047 hasPublicationYear "2019" @default.
- W2955544047 type Work @default.
- W2955544047 sameAs 2955544047 @default.
- W2955544047 citedByCount "8" @default.
- W2955544047 countsByYear W29555440472019 @default.
- W2955544047 countsByYear W29555440472020 @default.
- W2955544047 countsByYear W29555440472021 @default.
- W2955544047 crossrefType "posted-content" @default.
- W2955544047 hasAuthorship W2955544047A5027999421 @default.
- W2955544047 hasAuthorship W2955544047A5060182940 @default.
- W2955544047 hasAuthorship W2955544047A5066592325 @default.
- W2955544047 hasAuthorship W2955544047A5075079896 @default.
- W2955544047 hasConcept C107598950 @default.
- W2955544047 hasConcept C108583219 @default.
- W2955544047 hasConcept C111919701 @default.
- W2955544047 hasConcept C115537543 @default.
- W2955544047 hasConcept C119857082 @default.
- W2955544047 hasConcept C154945302 @default.
- W2955544047 hasConcept C173608175 @default.
- W2955544047 hasConcept C178489894 @default.
- W2955544047 hasConcept C199360897 @default.
- W2955544047 hasConcept C26713055 @default.
- W2955544047 hasConcept C2778476105 @default.
- W2955544047 hasConcept C2781215313 @default.
- W2955544047 hasConcept C38652104 @default.
- W2955544047 hasConcept C41008148 @default.
- W2955544047 hasConcept C739882 @default.
- W2955544047 hasConceptScore W2955544047C107598950 @default.
- W2955544047 hasConceptScore W2955544047C108583219 @default.
- W2955544047 hasConceptScore W2955544047C111919701 @default.
- W2955544047 hasConceptScore W2955544047C115537543 @default.
- W2955544047 hasConceptScore W2955544047C119857082 @default.