As neural networks (NNs) are increasingly used to provide edge intelligence, there is a growing need to make the edge devices that run them robust to faults. Edge devices must mitigate the resulting hardware failures while maintaining strict constraints on power, energy, latency, throughput, memory size, and computational resources. Edge NNs require fundamental changes in model architecture, e.g., quantization and fewer, smaller layers. PrioriFI is a more informed fault injection (FI) algorithm that evaluates edge NN robustness by ranking NN bits based on their fault sensitivity. PrioriFI prioritizes finding highly fault-sensitive bits, that is, the bits most critical to an NN's correctness, first. To accomplish this, PrioriFI uses the Hessian for the initial parameter ranking. Then, during an FI campaign, PrioriFI uses the information gained from past FIs as a heuristic so that future FIs target the bits likely to be the next most sensitive. With PrioriFI, designers can quickly evaluate different NNs and better co-design fault-tolerant edge NN systems.

Many verification methods have been proposed to detect microarchitectural information leakage in response to the surge of security breaches in hardware designs. These sophisticated efforts have gone a long way toward preventing attackers from breaking the system’s confidentiality. However, each approach has its own set of weaknesses: it may not be scalable enough, exhaustive enough, flexible enough to meet changing requirements or fit well into existing verification flows. We propose FastPath, a hybrid verification methodology that combines the efficiency of simulation with the exhaustive nature of formal verification. FastPath employs a structural analysis framework to automate the method further. Our experimental results compare FastPath to a state-of-the-art formal approach, showing a significant reduction in manual effort while achieving the same level of exhaustive confidence. We also discovered and contributed a fix for a previously unknown leak of internal operands in cv32e40s, a RISC-V processor intended for security applications.

Remote attackers can recover "FPGA pentimento" - long-removed data belonging to a prior user or proprietary design image on a cloud FPGA. Just as a pentimento of a painting can be exposed by infrared imaging, FPGA pentimentos can be exposed by signal timing sensors. The data constituting an FPGA pentimento is imprinted on the device through bias temperature instability effects on the underlying transistors. Measuring this degradation using a time-to-digital converter allows an attacker to (1) extract proprietary details or keys from an encrypted FPGA design image available on the AWS marketplace and (2) recover information from a previous user of a cloud-FPGA. These threat models are validated on AWS F1, with successful AES key recovery under one model.

The Arm Advanced eXtensible Interface (AXI) protocol is a widely used on-chip interconnect for processors, accelerators, memories, and other IPs. Any bugs in the AXI implementations pose a security risk to the chip's correctness. Buggy or non-compliant third-party IPs can use AXI implementation bugs to bypass the security mechanisms of the whole system. Identifying AXI implementation bugs is challenging because the incomplete specifications allow room for implementation-specific behavior in performant designs. EXPECT is a systematic approach for analyzing AXI implementations to detect functional and security violations. We use EXPECT to test 7 implementations of varying complexity, including the ones from AMD Xilinx and RISC-V PULP. We identified 135 property violations. We sampled 10 of them to show 7 exploits demonstrating that an attacker can use these bugs to trick victim IPs. Our exploits achieve outcomes such as using stale data, skipping reads and writes, leaking intermediate data, and reading and writing attacker-controlled data to attacker-controlled addresses. We evaluated our exploits in realistic scenarios deployed on FPGA. We show that AMD Xilinx protocol checker IPs miss 5/7 of our exploits.

Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simulations for performance validation in experimental software frameworks, verifying those ML models are robust under extreme quantization and pruning, and enabling ultra-fine-grained model inspection for efficient fault tolerance. We discuss approaches to developing and validating reliable algorithms at the scientific edge under such strict latency, resource, power, and area requirements in extreme experimental environments. We study metrics for developing robust algorithms, present preliminary results and mitigation strategies, and conclude with an outlook of these and future directions of research towards the longer-term goal of developing autonomous scientific experimentation methods for accelerated scientific discovery.

Deep neural networks use skip connections to improve training convergence. However, these skip connections are costly in hardware, requiring extra buffers and increasing on- and off-chip memory utilization and bandwidth requirements. In this article, we show that skip connections can be optimized for hardware when tackled with a hardware-software codesign approach. We argue that while a network’s skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware-efficient implementation with minimal to no accuracy loss. We introduce Tailor , a codesign tool whose hardware-aware training algorithm gradually removes or shortens a fully trained network’s skip connections to lower the hardware cost. Tailor improves resource utilization by up to 34% for block random access memories (BRAMs), 13% for flip-flops (FFs), and 16% for look-up tables (LUTs) for on-chip, dataflow-style architectures. Tailor increases performance by 30% and reduces memory bandwidth by 45% for a two-dimensional processing element array architecture.

Understanding the behavior of non-human primates is crucial for improving animal welfare, modeling social behavior, and gaining insights into distinctively human and phylogenetically shared behaviors. However, the lack of datasets on non-human primate behavior hinders in-depth exploration of primate social interactions, posing challenges to research on our closest living relatives. To address these limitations, we present ChimpACT, a comprehensive dataset for quantifying the longitudinal behavior and social relations of chimpanzees within a social group. Spanning from 2015 to 2018, ChimpACT features videos of a group of over 20 chimpanzees residing at the Leipzig Zoo, Germany, with a particular focus on documenting the developmental trajectory of one young male, Azibo. ChimpACT is both comprehensive and challenging, consisting of 163 videos with a cumulative 160,500 frames, each richly annotated with detection, identification, pose estimation, and fine-grained spatiotemporal behavior labels. We benchmark representative methods of three tracks on ChimpACT: (i) tracking and identification, (ii) pose estimation, and (iii) spatiotemporal action detection of the chimpanzees. Our experiments reveal that ChimpACT offers ample opportunities for both devising new methods and adapting existing ones to solve fundamental computer vision tasks applied to chimpanzee groups, such as detection, pose estimation, and behavior analysis, ultimately deepening our comprehension of communication and sociality in non-human primates.

Hardware security creates a hardware-based security foundation for secure and reliable operation of systems and applications used in our modern life. The presence of design for security, security assurance, and general security design life cycle practices in product life cycle of many large semiconductor design and manufacturing companies these days indicates that the importance of hardware security has been very well observed in industry. However, the high cost, time, and effort for building security into designs and assuring their security - due to using many manual processes - is still an important obstacle for economy of secure product development. This paper presents several promising directions for automation of design for security and security assurance practices to reduce the overall time and cost of secure product development. First, we present security verification challenges of SoCs, possible vulnerabilities that could be introduced inadvertently by tools mapping a design model in one level of abstraction to its lower level, and our solution to the problem by automatically mapping security properties from one level to its lower level incorporating techniques for extension and expansion of the properties. Then, we discuss the foundation necessary for further automation of formal security analysis of a design by incorporating threat model and common security vulnerabilities into an intermediate representation of a hardware model to be used to automatically determine if there is a chance for direct or indirect flow of information to compromise confidentiality or integrity of security assets. Finally, we discuss a pre-silicon-based framework for practical and time-and-cost effective power-side channel leakage analysis, root-causing the side-channel leakage by using the automatically generated leakage profile of circuit nodes, providing insight to mitigate the side-channel leakage by addressing the high leakage nodes, and assuring the effectiveness of the mitigation by reprofiling the leakage to prove its acceptable level of elimination. We hope that sharing these efforts and ideas with the security research community can accelerate the evolution of security-aware CAD tools targeted to design for security and security assurance to enrich the ecosystem to have tools from multiple vendors with more capabilities and higher performance.

System-on-chip (SoC) architectures are a heterogeneous mix of microprocessors, custom accelerators, memories, interfaces, peripherals, and other resources. These resources communicate using complex on-chip interconnect networks that attempt to quickly and efficiently arbitrate memory transactions whose behaviors can vary drastically depending on the current mode of operation and system operating state. Security- and safety-critical applications require access control policies that define how these resources interact to ensure that malicious and unsafe behaviors do not occur.Akeris a design and verification framework for on-chip access control. The core ofAkeris the access control wrapper (ACW)–a high-performance yet efficient hardware module that dynamically arbitrates on-chip communications.Akerdistributes ACWs across the SoC and programs them to perform local access control.Akerprovides a firmware generation tool and a property-driven security verification methodology to ensure that the ACWs are properly integrated and configured.Akersecurity verification confirms that the ACW behaves properly at IP level. It verifies the hardware root of trust firmware configures the ACW correctly. And it evaluates system-level security threats due to interactions between shared resources.Akeris experimentally validated on a Xilinx UltraScale+ programmable SoC. Additionally, anAkeraccess control system is integrated into the OpenPULP multicore archtiecture that uses OpenTitan hardware root-of-trust for firmware configuration.

Security verification is an important part of the hardware design process. Security verification teams can uncover weaknesses, vulnerabilities, and flaws. Unfortunately, the verification process involves substantial manual analysis to create the threat model, identify important security assets, articulate weaknesses, define security requirements, and specify security properties that formally describe security requirements upon the hardware. This work describes current hardware security verification practices. Many of these rely on manual analysis. We argue that the property generation process is a first step towards scalable and reproducible hardware security verification.

Modern systems on a chip (SoCs) utilize heterogeneous architectures where multiple IP cores have concurrent access to on-chip shared resources. In security-critical applications, IP cores have different privilege levels for accessing shared resources, which must be regulated by an access control system. Aker is a design and verification framework for SoC access control. Aker builds upon the Access Control Wrapper (ACW) - a high performance and easy-to-integrate hardware module that dynamically manages access to shared resources. To build an SoC access control system, Aker distributes the ACWs throughout the SoC, wrapping controller IP cores, and configuring the ACWs to perform local access control. To ensure the access control system is functioning correctly and securely, Aker provides a property-driven security verification using MITRE common weakness enumerations. Aker verifies the SoC access control at the IP level to ensure the absence of bugs in the functionalities of the ACW module, at the firmware level to confirm the secure operation of the ACW when integrated with a hardware root-of-trust (HRoT), and at the system level to evaluate security threats due to the interactions among shared resources. The performance, resource usage, and security of access control systems implemented through Aker is experimentally evaluated on a Xilinx UltraScale+ programmable SoC, it is integrated with the OpenTitan hardware root-of-trust, and it is used to design an access control system for the OpenPULP multicore architecture.