More Like this

1. {SoK}: All You Need to Know About {On-Device} {ML} Model Extraction - The Gap Between Research and Practice

   Nayan, Tushar; Guo, Qiming; Al_Duniawi, Mohammed; Botacin, Marcus; Uluagac, Selcuk; Sun, Ruimin (August 2024, USENIX)

   Balzarotti, Davide; Xu, Wenyuan (Ed.)

   On-device ML is increasingly used in different applications. It brings convenience to offline tasks and avoids sending user-private data through the network. On-device ML models are valuable and may suffer from model extraction attacks from different categories. Existing studies lack a deep understanding of on-device ML model security, which creates a gap between research and practice. This paper provides a systematization approach to classify existing model extraction attacks and defenses based on different threat models. We evaluated well known research projects from existing work with real-world ML models, and discussed their reproducibility, computation complexity, and power consumption. We identified the challenges for research projects in wide adoption in practice. We also provided directions for future research in ML model extraction security. 

   more » « less
2. SoK: Hardware Defenses Against Speculative Execution Attacks

   https://doi.org/10.1109/SEED51797.2021.00023  

   Hu, Guangyuan; He, Zecheng; Lee, Ruby B. (September 2021, 2021 International Symposium on Secure and Private Execution Environment Design (SEED))

   Speculative execution attacks leverage the speculative and out-of-order execution features in modern computer processors to access secret data or execute code that should not be executed. Secret information can then be leaked through a covert channel. While software patches can be installed for mitigation on existing hardware, these solutions can incur big performance overhead. Hardware mitigation is being studied extensively by the computer architecture community. It has the benefit of preserving software compatibility and the potential for much smaller performance overhead than software solutions. This paper presents a systematization of the hardware defenses against speculative execution attacks that have been proposed. We show that speculative execution attacks consist of 6 critical attack steps. We propose defense strategies, each of which prevents a critical attack step from happening, thus preventing the attack from succeeding. We then summarize 20 hardware defenses and overhead-reducing features that have been proposed. We show that each defense proposed can be classified under one of our defense strategies, which also explains why it can thwart the attack from succeeding. We discuss the scope of the defenses, their performance overhead, and the security-performance trade-offs that can be made. 

   more » « less
3. Time-Print: Authenticating USB Flash Drives with Novel Timing Fingerprints

   https://doi.org/10.1109/SP46214.2022.9833595  

   Cronin, Patrick; Gao, Xing; Wang, Haining; Cotton, Chase (May 2022, 2022 IEEE Symposium on Security and Privacy (SP))

   Universal Serial Bus (USB) ports are a ubiquitous feature in computer systems and offer a cheap and efficient way to provide power and data connectivity between a host and peripheral devices. Even with the rise of cloud and off-site computing, USB has played a major role in enabling data transfer between devices. Its usage is especially prevalent in high-security environments where systems are ‘air-gapped’ and not connected to the Internet. However, recent research has demonstrated that USB is not nearly as secure as once thought, with different attacks showing that modified firmware on USB mass storage devices can compromise a host system. While many defenses have been proposed, they require user interaction, advanced hardware support (incompatible with legacy devices), or utilize device identifiers that can be subverted by an attacker. In this paper, we present Time-Print, a novel timing-based fingerprinting method, for identifying USB mass storage devices. We create a fingerprint by timing a series of read operations from different locations on a drive, as the timing variations are unique enough to identify individual USB devices. Time-Print is low overhead, completely software-based, and does not require any extra or specialized hardware. To validate the efficacy of Time-Print, we examine more than 40 USB flash drives and conduct experiments in multiple authentication scenarios. The experimental results show that Time-Print can (1) identify known/unknown brand/model USB devices with greater than 99.5% accuracy, (2) identify seen/unseen devices of the same brand/model with 95% accuracy, and (3) classify USB devices from the same brand/model with an average accuracy of 98.7%. 

   more » « less
4. On the Pitfalls and Vulnerabilities of Schedule Randomization Against Schedule-Based Attacks

   https://doi.org/10.1109/RTAS.2019.00017  

   Nasri, Mitra; Chantem, Thidapat; Bloom, Gedare; Gerdes, Ryan M. (April 2019, 2019 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS))

   Schedule randomization is one of the recently introduced security defenses against schedule-based attacks, i.e., attacks whose success depends on a particular ordering between the execution window of an attacker and a victim task within the system. It falls into the category of information hiding (as opposed to deterministic isolation-based defenses) and is designed to reduce the attacker's ability to infer the future schedule. This paper aims to investigate the limitations and vulnerabilities of schedule randomization-based defenses in real-time systems. We first provide definitions, categorization, and examples of schedule-based attacks, and then discuss the challenges of employing schedule randomization in real-time systems. Further, we provide a preliminary security test to determine whether a certain timing relation between the attacker and victim tasks will never happen in systems scheduled by a fixed-priority scheduling algorithm. Finally, we compare fixed-priority scheduling against schedule-randomization techniques in terms of the success rate of various schedule-based attacks for both synthetic and real-world applications. Our results show that, in many cases, schedule randomization either has no security benefits or can even increase the success rate of the attacker depending on the priority relation between the attacker and victim tasks. 

   more » « less
5. Understanding and securing device vulnerabilities through automated bug report analysis

   Feng, X; Liao, X; Wang, X; Wang, H; Li, Q; Yang, K; Zhu, H; Sun, L. (January 2019, SEC'19: Proceedings of the 28th USENIX Conference on Security Symposium)

   Recent years have witnessed the rise of Internet-of-Things (IoT) based cyber attacks. These attacks, as expected, are launched from compromised IoT devices by exploiting security flaws already known. Less clear, however, are the fundamental causes of the pervasiveness of IoT device vulnerabilities and their security implications, particularly in how they affect ongoing cybercrimes. To better understand the problems and seek effective means to suppress the wave of IoT-based attacks, we conduct a comprehensive study based on a large number of real-world attack traces collected from our honeypots, attack tools purchased from the underground, and information collected from high-profile IoT attacks. This study sheds new light on the device vulnerabilities of today's IoT systems and their security implications: ongoing cyber attacks heavily rely on these known vulnerabilities and the attack code released through their reports; on the other hand, such a reliance on known vulnerabilities can actually be used against adversaries. The same bug reports that enable the development of an attack at an exceedingly low cost can also be leveraged to extract vulnerability-specific features that help stop the attack. In particular, we leverage Natural Language Processing (NLP) to automatically collect and analyze more than 7,500 security reports (with 12,286 security critical IoT flaws in total) scattered across bug-reporting blogs, forums, and mailing lists on the Internet. We show that signatures can be automatically generated through an NLP-based report analysis, and be used by intrusion detection or firewall systems to effectively mitigate the threats from today's IoT-based attacks. 

   more » « less