Anys Bacha bio photo

Anys Bacha

Assistant Professor at the University of Michigan

  G. Scholar LinkedIn Github e-Mail

Research

Dr. Bacha’s research focuses on the development of end-to-end solutions that address important challenges at the intersection of security and systems. In particular, his work explores novel defenses against new malware threats, investigating the vulnerabilities of emerging technologies to side-channel attacks, understanding the implications of online services on user privacy, as well as efficiently accelerating machine learning applications and how they can be seamlessly deployed in edge and cloud-based environments. His research contributions have been published in prestigious journals and conferences including papers that have received the Best Paper Award and honorable mentions in the distinguished IEEE Micro Top Picks. Dr. Bacha is the recipient of four NSF grants. In addition to the aforementioned, his research is demonstrated by industry impact through several issued patents.


Peer Reviewed Conference & Journal Publications

  • N. Lachtar, A. Abu Elkhail, A. Bacha, H. Malik
    An Application Agnostic Defense Against the Dark Arts of Cryptojacking
    IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2021.
    Acceptance Rate: 16.3% [BibTeX] [PDF] [Slides]

    @inproceedings{lachtar-dsn21,
      author = {Nada Lachtar and Abdulrahman Abu Elkhail and Anys Bacha and Hafiz Malik},
      title = {An Application Agnostic Defense Against the Dark Arts of Cryptojacking},
      booktitle = {51st International Conference on Dependable Systems and Networks ({DSN} 2021)},
      year = {2021},
      isbn = {978-1-939133-18-2},
      address = {Taipei},
      pages = {413--426},
      publisher = { {IEEE/IFIP}},
      month = jun
    }  
    
  • A. Abu Elkhail, R. Refat, R. Habre, A. Hafeez, A. Bacha, H. Malik
    Vehicle Security: A Survey of Security Issues and Vulnerabilities, Malware Attacks and Defenses
    IEEE Access, 2021.
    H-index: 158, Impact Factor: 3.7 [BibTeX] [PDF]

    @inproceedings{elkhail-access21,
      author = {Elkhail, Abdulrahman Abu and Refat, Rafi Ud Daula and Habre, Ricardo and Hafeez, Azeem and Bacha, Anys and Malik, Hafiz},
      title = {Vehicle Security: A Survey of Security Issues and Vulnerabilities, Malware Attacks and Defenses},
      journal={IEEE Access},
      year={2021},
      volume={9},
      pages={162401-162437},
      doi={10.1109/ACCESS.2021.3130495}
    }  
    
  • D. Ibdah, N. Lachtar, S. Raparthi, A. Bacha
    "Why Should I Read the Privacy Policy, I Just Need the Service": A Study on Attitudes and Perceptions Towards Privacy Policies
    IEEE Access, 2021.
    H-index: 158, Impact Factor: 3.7 [BibTeX] [PDF]

    @inproceedings{ibdah-access21,
      author = {Duha Ibdah and Nada Lachtar and Satya Meenakshi Raparthi and Anys Bacha},
      title = {Ibdah, Duha and Lachtar, Nada and Raparthi, Satya Meenakshi and Bacha, Anys},
      journal={IEEE Access},
      year = {2021},
      volume={9},
      pages={166465-166487},
      doi={10.1109/ACCESS.2021.3130086}
    }  
    
  • D. Ibdah, N. Lachtar, A. Abu Elkhail, A. Bacha, H. Malik
    Dark Firmware: A Systematic Approach to Exploring Application Security Risks in the Presence of Untrusted Firmware
    International Symposium on Research in Attacks, Intrusions and Defenses (RAID), 2020.
    Acceptance Rate: 25.6% [BibTeX] [PDF] [Slides]

    @inproceedings{ibdah-raid20,
      author = {Duha Ibdah and Nada Lachtar and Abdulrahman Abu Elkhail and Anys Bacha and Hafiz Malik},
      title = {Dark Firmware: A Systematic Approach to Exploring Application Security Risks in the Presence of Untrusted Firmware},
      booktitle = {23rd International Symposium on Research in Attacks, Intrusions and Defenses ({RAID} 2020)},
      year = {2020},
      isbn = {978-1-939133-18-2},
      address = {San Sebastian},
      pages = {413--426},
      url = {https://www.usenix.org/conference/raid2020/presentation/ibdah},
      publisher = { {USENIX} Association},
      month = oct
    }  
    
  • N. Lachtar, D. Ibdah, A. Bacha
    Towards Mobile Malware Detection Through Convolutional Neural Networks
    IEEE Embedded Systems Letters (ESL), 2020.
    H-index: 28, Impact Factor: 1.5 [BibTeX] [PDF]

    @article{lachtar-esl20,
      author={Lachtar, Nada and Ibdah, Duha and Bacha, Anys},
      journal={IEEE Embedded Systems Letters}, 
      title={Toward Mobile Malware Detection Through Convolutional Neural Networks}, 
      year={2021},
      volume={13},
      number={3},
      pages={134-137},
      doi={10.1109/LES.2020.3035875}}
    
    
  • N. Lachtar, A. Abu Elkhail, A. Bacha, H. Malik
    A Cross-stack Approach Towards Defending Against Cryptojacking
    IEEE Computer Architecture Letters (CAL), 2020.
    H-index: 36, Impact Factor: 1.6 [BibTeX] [PDF] [Slides]

    @inproceedings{lachtar-cal20,
      author={N. {Lachtar} A. {Abu Elkhail} and A. {Bacha} and H. {Malik}}, 
      title = {A Cross-stack Approach Towards Defending Against Cryptojacking},
      booktitle = {IEEE Computer Architecture Letters (CAL)},
      year = {2020},
      volume={19},
      number={2}, 
      pages = {126-129},
      keywords={cryptojacking, cryptocurrency mining, malware, security}
    }  
    
  • M. Samavatian, A. Bacha, L. Zhou, R. Teodorescu
    RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory
    ACM Journal on Emerging Technologies in Computing Systems (JETC), 2020.
    H-index: 40, Impact Factor: 2.3 [BibTeX] [PDF]

    @article{samavatian_jetc20,
      author = {Samavatian, Mohammad Hossein and Bacha, Anys and Zhou, Li and Teodorescu, Radu},
      title = {RNNFast: An Accelerator for Recurrent Neural Networks Using Domain-Wall Memory},
      year = {2020},
      issue_date = {October 2020},
      publisher = {Association for Computing Machinery},
      address = {New York, NY, USA},
      volume = {16},
      number = {4},
      issn = {1550-4832},
      url = {https://doi.org/10.1145/3399670},
      doi = {10.1145/3399670},
      abstract = {Recurrent Neural Networks (RNNs) are an important class of neural networks designed to retain and incorporate context into current decisions. RNNs are particularly well suited for machine learning problems in which context is important, such as speech recognition and language translation.This work presents RNNFast, a hardware accelerator for RNNs that leverages an emerging class of non-volatile memory called domain-wall memory (DWM). We show that DWM is very well suited for RNN acceleration due to its very high density and low read/write energy. At the same time, the sequential nature of input/weight processing of RNNs mitigates one of the downsides of DWM, which is the linear (rather than constant) data access time.RNNFast is very efficient and highly scalable, with flexible mapping of logical neurons to RNN hardware blocks. The basic hardware primitive, the RNN processing element (PE), includes custom DWM-based multiplication, sigmoid and tanh units for high density and low energy. The accelerator is designed to minimize data movement by closely interleaving DWM storage and computation. We compare our design with a state-of-the-art GPGPU and find 21.8\texttimes{} higher performance with 70\texttimes{} lower energy.},
      journal = {J. Emerg. Technol. Comput. Syst.},
      month = sep,
      articleno = {38},
      numpages = {27},
      keywords = {domain-wall memory, LSTM, accelerator, Recurrent neural networks}
    }
    
    
    
    
  • K. Barber, A. Bacha, L. Zhou, Y. Zhang, R. Teodorescu
    SpecShield: Shielding Speculative Data from Leaky Side Channels
    International Conference on Parallel Architectures and Compilation Techniques (PACT), 2019.
    IEEE Micro Top Picks Honorable Mention
    Acceptance Rate: 20.6% [BibTeX] [PDF] [Slides]

    @inproceedings{barber-pact19,
      author={K. {Barber} and A. {Bacha} and L. {Zhou} and Y. {Zhang} and R. {Teodorescu}}, 
      title = {SpecShield: Shielding Speculative Data from Leaky Side Channels},
      booktitle = {International Conference on Parallel Architectures and Compilation Techniques (PACT)},
      year = {2019},
      pages = {151-164}
    }  
    
  • K. Barber, A. Bacha, L. Zhou, Y. Zhang, R. Teodorescu
    Isolating Speculative Data to Prevent Transient Execution Attacks
    IEEE Computer Architecture Letters (CAL), 2019.
    Best Paper Award
    Presented at International Symposium on High-Performance Computer Architecture (HPCA), 2020
    and Hardware and Architectural Support for Security and Privacy (HASP), 2019.
    H-index: 36, Impact Factor: 1.6 [BibTeX] [PDF] [Slides]

    @ARTICLE{barber-cal19, 
    author={K. {Barber} and A. {Bacha} and L. {Zhou} and Y. {Zhang} and R. {Teodorescu}}, 
    journal={IEEE Computer Architecture Letters}, 
    title={Isolating Speculative Data to Prevent Transient Execution Attacks}, 
    year={2019}, 
    volume={18}, 
    number={2}, 
    pages={178-181}, 
    keywords={hardware security, transient execution attacks, covert timing channels}, 
    month={}
    }
    
  • L. Zhou, M. Samavatian, A. Bacha, S. Majumdar, R. Teodorescu
    Adaptive Parallel Execution of Deep Neural Networks on Heterogeneous Edge Devices
    ACM/IEEE Symposium on Edge Computing (SEC), 2019.
    [BibTeX] [PDF] [Slides]

    @inproceedings{zhou-sec19,
      author={L. {Zhou} and M. {Samavatian} and A. {Bacha} and R. {Teodorescu}}, 
      title = {Adaptive Parallel Execution of Deep Neural Networks on
    Heterogeneous Edge Devices},
      booktitle = {ACM/IEEE Symposium on Edge Computing (SEC)},
      year = {2019},
      isbn = {9781450367332},
      publisher = {Association for Computing Machinery},
      address = {New York, NY, USA},
      url = {https://doi.org/10.1145/3318216.3363312},
      doi = {10.1145/3318216.3363312},
      pages = {195–208},
      numpages = {14},
      keywords = {parallel execution, inference, deep learning, edge devices},
      location = {Arlington, Virginia},
      series = {SEC ’19}
    }
    
  • N. Lachtar, D. Ibdah, A. Bacha
    The Case for Native Instructions in the Detection of Mobile Ransomware
    IEEE Letters of Computer Society (LOCS), 2019.
    [BibTeX] [PDF]

    @ARTICLE{lachtar-locs19, 
    author={N. {Lachtar} and D. {Ibdah} and A. {Bacha}}, 
    journal={IEEE Letters of the Computer Society}, 
    title={The Case for Native Instructions in the Detection of Mobile Ransomware}, 
    year={2019}, 
    volume={2}, 
    number={2}, 
    pages={16-19}, 
    keywords={Android (operating system);instruction sets;invasive software;learning (artificial intelligence);mobile computing;XML;XML-based permission files;native instructions;detecting ransomware;instruction opcodes;contemporary instruction;mobile segment;mobile users;high level bytecode;machine code;machine learning models;ransomware families;mobile ransomware samples;Android malware dataset;instruction set;obfuscation techniques;Ransomware;Training;Support vector machines;Mathematical model;Prediction algorithms;Ransomware;Android Malware;mobile security;instruction set architecture;machine learning}, 
    doi={10.1109/LOCS.2019.2918091}, 
    ISSN={2573-9689}, 
    month={June},}
    
  • X. Pan, A. Bacha, S. Rudolph, L. Zhou, Y. Zhang, R. Teodorescu
    NVCool: When Non-Volatile Caches Meet Cold Boot Attacks
    IEEE International Conference on Computer Design (ICCD), 2018.
    Acceptance Rate: 28.9% [BibTeX] [PDF] [Slides]

    @inproceedings{pan-iccd18,
      author = {Xiang Pan and Anys Bacha and Spencer Rudolph and Li Zhou and Yinqian Zhang and Radu Teodorescu},
      title = {NVCool: When Non-Volatile Caches Meet Cold Boot Attacks},
      booktitle = {IEEE International Conference on Computer Design (ICCD)},
      year = {2018},
      pages = {439-448}
    }
    
  • X. Pan, A. Bacha, R. Teodorescu
    Respin: Rethinking Near-Threshold Multiprocessor Design with Non-Volatile Memory
    IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2017.
    Acceptance Rate: 22.4% [BibTeX] [PDF] [Slides]

    @inproceedings{pan-ipdps17,
      author = {Xiang Pan and Anys Bacha and Radu Teodorescu},
      title = {Respin: Rethinking Near-Threshold Multiprocessor Design with Non-volatile Memory},
      booktitle = {IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
      year = {2017},
      pages = {265--275}
    }
    
  • A. Bacha, R. Teodorescu
    Authenticache: Harnessing Cache ECC for System Authentication
    IEEE International Symposium on Microarchitecture (MICRO), 2015.
    IEEE Micro Top Picks Honorable Mention
    Acceptance Rate: 21.3% [BibTeX] [PDF] [Slides]

    @inproceedings{bacha-micro15,
      author = {Anys Bacha and Radu Teodorescu},
      title = {Authenticache: {Harnessing} Cache {ECC} for System Authentication},
      booktitle = {International Symposium on Microarchitecture (MICRO)},
      year = {2015},
      month = {December},
      pages = {1 -- 12}
    }
    
  • A. Bacha, R. Teodorescu
    Using ECC Feedback to Guide Voltage Speculation in Low-Voltage Processors
    IEEE International Symposium on Microarchitecture (MICRO), 2014.
    Acceptance Rate: 19.4% [BibTeX] [PDF] [Slides]

    @inproceedings{bacha-micro14,
    author={Anys Bacha and Radu Teodorescu}, 
    booktitle=micro,
    title={Using {ECC} Feedback to Guide Voltage Speculation in Low-Voltage Processors},
    year={2014}, 
    month={December}, 
    pages={297--307},
    }
    
  • A. Bacha, R. Teodorescu
    Dynamic Reduction of Voltage Margins by Leveraging On-chip ECC in Itanium II Processors
    ACM International Symposium on Computer Architecture (ISCA), 2013.
    Acceptance Rate: 19.4% [BibTeX] [PDF]

    @inproceedings{bacha-isca13,
      author = {Anys Bacha and Radu Teodorescu},
      title = {Dynamic Reduction of Voltage Margins by Leveraging On-chip {ECC in Itanium
      II} Processors},
      booktitle = {International Symposium on Computer Architecture (ISCA)},
      year = {2013},
      month = {June},
      pages = {297--307}
    }
    

Patents

  • A. Bacha
    Log events for root cause error diagnosis
    U.S. Patent 10579459, 2020.
    [BibTeX] [PDF]

    @patent{bacha-usptomar2020,
      author = {A. Bacha},
      title = {Log events for root cause error diagnosis},
      year = {2020},
      number = {U.S. Patent 10579459, 2020}
    }
    
  • A. Bacha, and D. Hamid
    Baseboard Management Controller To Deconfigure Field Replaceable Units According To Deep Learning Model
    U.S. Patent 10552729, 2020.
    [BibTeX] [PDF]

    @patent{bacha-usptofeb2020,
      author = {A. Bacha and D. Hamid},
      title = {Baseboard Management Controller To Deconfigure Field Replaceable Units According To Deep Learning Model},
      year = {2020},
      number = {U.S. Patent 10552729, 2020}
    }
    
  • A. Bacha
    Obscuration of a cache signal
    U.S. Patent 10318431, 2019.
    [BibTeX] [PDF]

    @patent{bacha-usptojun2019,
      author = {A. Bacha},
      title = {Obscuration of a cache signal},
      year = {2019},
      number = {U.S. Patent 10318431, 2019}
    }
    
  • A. Bacha
    Assigning processors to memory mapped configuration
    U.S. Patent 9940291, 2018.
    [BibTeX] [PDF]

    @patent{bacha-usptoapr2018,
      author = {A. Bacha, T. Pham, T. Gorenc},
      title = {Assigning processors to memory mapped configuration},
      year = {2018},
      number = {U.S. Patent 9940291, 2018}
    }
    
  • A. Bacha
    Access cache line from lower level cache
    U.S. Patent 9965391, 2018.
    [BibTeX] [PDF]

    @patent{bacha-usptomay2018,
      author = {A. Bacha},
      title = {Access cache line from lower level cache},
      year = {2018},
      number = {US Patent 9965391, 2018}
    }
    
  • A. Bacha
    Template copy to cache
    U.S. Patent 10109370, 2018.
    [BibTeX] [PDF]

    @patent{bacha-usptooct2018,
      author = {A. Bacha},
      title = {Template copy to cache},
      year = {2018},
      number = {U.S. Patent 10109370, 2018}
    }
    
  • A. Bacha
    Determine voltage supplied to a core
    U.S. Patent 9342123, 2016.
    [BibTeX] [PDF]

    @patent{bacha-usptojun2016,
      author = {A. Bacha},
      title = {Determine voltage supplied to a core},
      year = {2016},
      number = {U.S. Patent 9342123}
    }
    
  • A. Bacha and T. Pham
    System and methods for sharing platform data with an ACPI module of a computer system
    U.S. Patent 8347070, 2013.
    [BibTeX] [PDF]

    @patent{bacha-usptojul2013,
      author = {A. Bacha and T. Pham},
      title = {System and methods for sharing platform data with an ACPI module of a computer system},
      year = {2013},
      number = {U.S. Patent 8347070}
    }
    
  • S. Huang and A. Bacha
    Leakage current protection circuit
    U.S. Patent 7768756, 2010.
    [BibTeX] [PDF]

    @patent{huang-usptojul2010,
      author = {S. Huang and A. Bacha},
      title = {Leakage current protection circuit},
      year = {2010},
      number = {U.S. Patent 7768756}
    }
    
  • A. Bacha
    Optimizing Event Logging Using Deep Recurrent Neural Networks
    U.S. Patent Pending, 2017.
    [BibTeX] [PDF]

    @patent{bacha-usptomar2017,
      author = {A. Bacha},
      title = {Optimizing Event Logging Using Deep Recurrent Neural Networks},
      year = {2017},
      number = {U.S. Patent Pending, 2017}
    }
    
  • A. Bacha, B. Winnick and T. Vaden
    Core characterization for processor cores
    World Patent Pending WO2017131667 A1, 2016.
    [BibTeX] [PDF]

    @patent{bacha-usptojul2016,
      author = {A. Bacha, B. Winick, and T. Vaden},
      title = {Core characterization for processor cores},
      year = {2016},
      number = {World Patent Pending WO2017131667 A1, 2016}
    }
    
  • A. Bacha
    Obscuration of a Cache Signal
    World Patent Pending WO2017048257, 2015.
    [BibTeX] [PDF]

    @patent{bacha-usptosep2015,
      author = {A. Bacha},
      title = {Obscuration of a Cache Signal},
      year = {2015},
      number = {World Patent Pending WO2017048257 A1, 2015}
    }
    
  • A. Bacha
    Assign Error Rate to Memory
    World Patent Pending WO2016039767, 2014.
    [BibTeX] [PDF]

    @patent{bacha-usptosep2014,
      author = {A. Bacha},
      title = {Assign Error Rate to Memory},
      year = {2015},
      number = {World Patent Pending WO2016039767 A1, 2014}
    }
    
  • A. Bacha
    Voltage selectors coupled to processor cores
    World Patent Pending WO2015183268, 2014.
    [BibTeX] [PDF]

    @patent{bacha-usptomay2014,
      author = {A. Bacha},
      title = {Voltage selectors coupled to processor cores},
      year = {2014},
      number = {World Patent Pending WO2015183268 A1, 2014}
    }