FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4303648996> ?p ?o ?g. }

• W4303648996 abstract "Determining whether multiple instructions can access the same memory location is a critical task in binary analysis. It is challenging as statically computing precise alias information is undecidable in theory. The problem aggravates at the binary level due to the presence of compiler optimizations and the absence of symbols and types. Existing approaches either produce significant spurious dependencies due to conservative analysis or scale poorly to complex binaries. We present a new machine-learning-based approach to predict memory dependencies by exploiting the model's learned knowledge about how binary programs execute. Our approach features (i) a self-supervised procedure that pretrains a neural net to reason over binary code and its dynamic value flows through memory addresses, followed by (ii) supervised finetuning to infer the memory dependencies statically. To facilitate efficient learning, we develop dedicated neural architectures to encode the heterogeneous inputs (i.e., code, data values, and memory addresses from traces) with specific modules and fuse them with a composition learning strategy. We implement our approach in NeuDep and evaluate it on 41 popular software projects compiled by 2 compilers, 4 optimizations, and 4 obfuscation passes. We demonstrate that NeuDep is more precise (1.5x) and faster (3.5x) than the current state-of-the-art. Extensive probing studies on security-critical reverse engineering tasks suggest that NeuDep understands memory access patterns, learns function signatures, and is able to match indirect calls. All these tasks either assist or benefit from inferring memory dependencies. Notably, NeuDep also outperforms the current state-of-the-art on these tasks." @default.
• W4303648996 created "2022-10-08" @default.
• W4303648996 creator A5005776608 @default.
• W4303648996 creator A5007048525 @default.
• W4303648996 creator A5016425387 @default.
• W4303648996 creator A5023589581 @default.
• W4303648996 creator A5048358055 @default.
• W4303648996 creator A5056288677 @default.
• W4303648996 creator A5057214714 @default.
• W4303648996 creator A5064541855 @default.
• W4303648996 creator A5074654320 @default.
• W4303648996 date "2022-11-07" @default.
• W4303648996 modified "2023-09-26" @default.
• W4303648996 title "NeuDep: neural binary memory dependence analysis" @default.
• W4303648996 cites W1507654557 @default.
• W4303648996 cites W1582456956 @default.
• W4303648996 cites W1972429847 @default.
• W4303648996 cites W2004633100 @default.
• W4303648996 cites W2010204191 @default.
• W4303648996 cites W2018107877 @default.
• W4303648996 cites W2030906223 @default.
• W4303648996 cites W2140609933 @default.
• W4303648996 cites W2151135920 @default.
• W4303648996 cites W2296073425 @default.
• W4303648996 cites W2296467253 @default.
• W4303648996 cites W22973579 @default.
• W4303648996 cites W2297774820 @default.
• W4303648996 cites W2344444819 @default.
• W4303648996 cites W2408027109 @default.
• W4303648996 cites W2480466304 @default.
• W4303648996 cites W2516933175 @default.
• W4303648996 cites W2548165777 @default.
• W4303648996 cites W2753873057 @default.
• W4303648996 cites W2765363641 @default.
• W4303648996 cites W2899384793 @default.
• W4303648996 cites W2926178846 @default.
• W4303648996 cites W2963868406 @default.
• W4303648996 cites W2963935794 @default.
• W4303648996 cites W2967047440 @default.
• W4303648996 cites W2969773072 @default.
• W4303648996 cites W2979367728 @default.
• W4303648996 cites W2979393298 @default.
• W4303648996 cites W3000514891 @default.
• W4303648996 cites W3012221736 @default.
• W4303648996 cites W3031914912 @default.
• W4303648996 cites W3033775865 @default.
• W4303648996 cites W3093415205 @default.
• W4303648996 cites W3100869085 @default.
• W4303648996 cites W3134135611 @default.
• W4303648996 cites W3135005174 @default.
• W4303648996 cites W3139338820 @default.
• W4303648996 cites W3157291566 @default.
• W4303648996 cites W3159942024 @default.
• W4303648996 cites W3162962341 @default.
• W4303648996 cites W3163448030 @default.
• W4303648996 cites W3176740355 @default.
• W4303648996 cites W3193682477 @default.
• W4303648996 cites W3194813479 @default.
• W4303648996 cites W3196001856 @default.
• W4303648996 cites W3212166010 @default.
• W4303648996 cites W3215052868 @default.
• W4303648996 cites W4206312123 @default.
• W4303648996 cites W4210626567 @default.
• W4303648996 cites W4220672926 @default.
• W4303648996 cites W4226057883 @default.
• W4303648996 cites W4282593910 @default.
• W4303648996 cites W4284665627 @default.
• W4303648996 cites W4284687350 @default.
• W4303648996 cites W4285490409 @default.
• W4303648996 cites W4296938538 @default.
• W4303648996 cites W4308632257 @default.
• W4303648996 cites W4312727366 @default.
• W4303648996 cites W79064388 @default.
• W4303648996 doi "https://doi.org/10.1145/3540250.3549147" @default.
• W4303648996 hasPublicationYear "2022" @default.
• W4303648996 type Work @default.
• W4303648996 citedByCount "0" @default.
• W4303648996 crossrefType "proceedings-article" @default.
• W4303648996 hasAuthorship W4303648996A5005776608 @default.
• W4303648996 hasAuthorship W4303648996A5007048525 @default.
• W4303648996 hasAuthorship W4303648996A5016425387 @default.
• W4303648996 hasAuthorship W4303648996A5023589581 @default.
• W4303648996 hasAuthorship W4303648996A5048358055 @default.
• W4303648996 hasAuthorship W4303648996A5056288677 @default.
• W4303648996 hasAuthorship W4303648996A5057214714 @default.
• W4303648996 hasAuthorship W4303648996A5064541855 @default.
• W4303648996 hasAuthorship W4303648996A5074654320 @default.
• W4303648996 hasBestOaLocation W43036489962 @default.
• W4303648996 hasConcept C111919701 @default.
• W4303648996 hasConcept C153247305 @default.
• W4303648996 hasConcept C154945302 @default.
• W4303648996 hasConcept C169590947 @default.
• W4303648996 hasConcept C199360897 @default.
• W4303648996 hasConcept C33923547 @default.
• W4303648996 hasConcept C41008148 @default.
• W4303648996 hasConcept C48372109 @default.
• W4303648996 hasConcept C63435697 @default.
• W4303648996 hasConcept C80444323 @default.
• W4303648996 hasConcept C94375191 @default.
• W4303648996 hasConcept C98986596 @default.

• next