Mitigating Shift-Based Covert-Channel Attacks in Racetrack Last Level Caches

被引:0
|
作者
Zhao, Lei [1 ]
Zhang, Youtao [1 ]
Yang, Jun [1 ]
机构
[1] Univ Pittsburgh, Pittsburgh, PA 15260 USA
关键词
Racetrack Memory; Covert Channel; Last Level Cache;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Racetrack memory (RM, also known DWM (domain wall memory)) is an emerging memory technology that has many advantages such as low power, high density, and low access latency. Recent studies have shown that it is promising to architect RM as last level cache (LLC). Given that a RM track consists of m domains (for storing m bits data) and n access heads (1 <= n < m,), one RM access often requires multiple hops of shift to move the access head above the domain to he accessed. This leads to variant access latency, which may be exploited to initiate covert channel attacks to leak sensitive information in secure computing environment,. In this paper, we elaborate the feasibility of such attacks and propose secure head management policies to effectively mitigate the attacks in RM LLCs. Our experimental results show that the proposed schemes can reduce the new discovered shift-based covert channel's capacity by up to 260 times with modest performance overhead.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] GPUGuard: Mitigating Contention Based Side and Covert Channel Attacks on GPUs
    Xu, Qiumin
    Naghibijouybari, Hoda
    Wang, Shibo
    Abu-Ghazaleh, Nael
    Annavaram, Murali
    INTERNATIONAL CONFERENCE ON SUPERCOMPUTING (ICS 2019), 2019, : 497 - 509
  • [2] Cache Template Attacks: Automating Attacks on Inclusive Last-Level Caches
    Gruss, Daniel
    Spreitzer, Raphael
    Mangard, Stefan
    PROCEEDINGS OF THE 24TH USENIX SECURITY SYMPOSIUM, 2015, : 897 - 912
  • [3] RIC: Relaxed Inclusion Caches for Mitigating LLC Side-Channel Attacks
    Kayaalp, Mehmet
    Khasawneh, Khaled N.
    Esfeden, Hodjat Asghari
    Elwell, Jesse
    Abu-Ghazaleh, Nael
    Ponomarev, Dmitry
    Jaleel, Aamer
    PROCEEDINGS OF THE 2017 54TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2017,
  • [4] Power and Energy Reduction of Racetrack-based Caches by Exploiting Shared Shift Operations
    Larimi, Seyed Saber Nabavi
    Kamal, Mehdi
    Afzali-Kusha, Ali
    Mahmoodi, Hamid
    2016 IFIP/IEEE INTERNATIONAL CONFERENCE ON VERY LARGE SCALE INTEGRATION (VLSI-SOC), 2016,
  • [5] Spy Cartel: Parallelizing Evict+Time-Based Cache Attacks on Last-Level Caches
    Himanshi Jain
    D. Anthony Balaraju
    Chester Rebeiro
    Journal of Hardware and Systems Security, 2019, 3 (2) : 147 - 163
  • [6] C3APSULe: Cross-FPGA Covert-Channel Attacks through Power Supply Unit Leakage
    Giechaskiel, Ilias
    Rasmussen, Kasper Bonne
    Szefer, Jakub
    2020 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP 2020), 2020, : 1728 - 1741
  • [7] An Efficient Approach for Mitigating Covert Storage Channel Attacks in Virtual Machines by the Anti-Detection Criterion
    Chong Wang
    Nasro Min-Allah
    Bei Guan
    Yu-Qi Lin
    Jing-Zheng Wu
    Yong-Ji Wang
    Journal of Computer Science and Technology, 2019, 34 : 1351 - 1365
  • [8] An Efficient Approach for Mitigating Covert Storage Channel Attacks in Virtual Machines by the Anti-Detection Criterion
    Wang, Chong
    Min-Allah, Nasro
    Guan, Bei
    Lin, Yu-Qi
    Wu, Jing-Zheng
    Wang, Yong-Ji
    JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2019, 34 (06) : 1351 - 1365
  • [9] Comparative analysis of STT and SOT based MRAMs for last level caches
    Saha, Rajesh
    Pundir, Yogendra Pratap
    Pal, Pankaj Kumar
    JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS, 2022, 551
  • [10] Last-Level Cache Side-Channel Attacks are Practical
    Liu, Fangfei
    Yarom, Yuval
    Ge, Qian
    Heiser, Gernot
    Lee, Ruby B.
    2015 IEEE SYMPOSIUM ON SECURITY AND PRIVACY SP 2015, 2015, : 605 - 622