Deep Neural Networks are widely used in multiple applications, but their security is threatened by backdoor attacks, where adversaries inject stealthy triggers into training dataset to manipulate the predictions of the model. Existing defenses, such as pruning and distillation suffer from a trade-off between defense performance and Clean Accuracy (CA), especially under low poisoning rate (e.g. 1%) or stealthy attacks. To address this challenge, we propose a Hybrid Neuro-Purification (HNP) framework, which integrates stochastic noise injection with global adversarial fine-tuning. Compared to traditional hard pruning methods, our approach adopts a soft scheme to disentangle sparse backdoor neurons from benign features without permanent removal. Experiments on CIFAR-10 and Tiny ImageNet demonstrate that the HNP outperforms benchmark defenses: it achieves a 1.07% average Attack Success Rate (ASR) across five attacks, suppresses the ASR to 4.53% on WaNet, and maintains clean accuracy > 92% even under 1% poisoning rate, solving the trade-off where baseline methods suffer from significant degradation in clean accuracy.

With increasing computation of various applications, dynamic voltage and frequency scaling (DVFS) is gradually deployed on FPGAs to improve performance and save energy. However, its reliability and security have not been sufficiently evaluated, which incurs quite many concerns. In this article, we propose an evaluation framework for deep investigation of stealthy DVFS fault injection attacks on the state-of-the-art deep neural networks (DNNs) deployed on modern FPGAs. The evaluation framework mainly consists of a DVFS attack striker and a time-to-digital converter (TDC)-based hardware profiler. Two modes of evaluation are derived, and their effectiveness is demonstrated on a platform composed of a SkyNet accelerator and three ImageNet models built on a Xilinx deep learning processor unit (DPU). Experimental results show that more than 99% detection accuracy loss can be measured targeting at all tested DNN models under prospective operation mode but without any performance degradation in frame per second (FPS). In our investigation of sensitive layer mode, more than 93% average accuracy loss with 84.7% fault probability can be measured on a single bundle of the SkyNet. We characterize the vulnerabilities of different DNN layers subject to DVFS attacks through leveraging the TDC-based hardware profiler to precisely control the timing of fault injection.

Fault injection attacks (FIAs) are a class of active physical attacks that inject faults into computing devices to deliberately change their intended behaviors for malicious purposes such as security feature circumvention, privilege escalation, secret data extraction by analyzing the erroneous outputs, etc. Existing sensors that detect fault injection attacks are either susceptible to aging or suffer from complicated and costly calibration process. Worse still, most sensors will fail in the presence of dynamic voltage and frequency scaling (DVFS) because they are built upon fixed delay chains and cannot adapt to operating voltage and frequency variations. In this paper, we overcome these limitations by presenting CDS, a delay chain based digital sensor that exploits timing variations of both detector and protected object for detecting multiple types of fault injection attacks. CDS utilizes a calibration module to solve the accuracy degradation caused by aging phenomena and a dynamic adjustment module to acclimatize itself to the need of dynamically adjusting voltage according to operating frequency in the presence of DVFS. To demonstrate its capability, we use CDS to protect the hardware accelerator of PRESENT cryptographic algorithm against voltage and laser glitching attacks. Simulation results based on HSPICE show that (i) CDS can detect 100% of voltage and temperature coordinated glitching attacks with 4.1% early warning; (ii) CDS can detect 100% of laser glitching attacks with 9.1% early warning; (iii) CDS maintains outstanding aging resistance with only 1.1% false alarm rate increase after 7 years of use.

As a common defense against side-channel attacks, random delay insertion introduces noise into the executive flow of encryption, which increases attack complexity. Accordingly, various techniques are exploited to mitigate the defense effect of such insertions. As an advanced mathematical technique, wavelet analysis is considered to be a more effective technology according to its detailed and comprehensive interpretation of signals. In this paper, we propose a unified and fully automated wavelet-based attack framework (denoted asUWAF), whose data processing is kept within one unified wavelet domain, with three enhanced components: denoising, alignment and key extraction. We put forward a new idea of combining machine learning with wavelet analysis to realize the full automation of the program for attack framework, rendering it possible to search exhaustively for the optimal combination of parameter settings in wavelet transform. Our proposal finds a new setting of wavelet parameters that have not been exploited ever before and achieves the performance enhancement for about 20 times fewer traces required for successful key recovery.UWAFis compared with several mainstream attack frameworks. Experimental results show that it outperforms those counterparts, and can be considered as an effective framework-level solution to defeat the countermeasure of random delay insertion.

Chipless Radio Frequency Identification (RFID) tags that do not include an integrated circuit (IC) in the transponder are more appropriate for supply-chain management of low-cost commodities and have been gaining extensive attention due to their relatively lower price. However, existing chipless RFID tags consume considerable tag area and manufacturing time/cost because of complex fabrication process (e.g., requiring removing or shorting some resonators on the tag substrate to encode data). Worse still, their identifiers (IDs) are deterministic, clonable, and small in terms of bitwidth. To address these shortcomings and help preserve the cold chain for commodities (e.g., vaccines, pharmaceuticals, etc.) sensitive to temperature, we develop a novel unclonable environmentally sensitive chipless RFID (UCR) tag that intrinsically generates a unique ID from both manufacturing variations and ambient temperature variation. A UCR tag consists of two parts: (i) a certain number of concentric ring slot resonators integrated on a certain laminate (e.g., TACONIC TLX-0), whose resonance frequencies rely on geometric parameters of slot resonators and dielectric constant of substrate material that are sensitive to manufacturing variations, and (ii) a stand-alone circular ring slot resonator integrated on a particular substrate (e.g., grease) that will be melted at a high temperature, whose resonance frequency relies on geometric parameters of slot resonator, dielectric constant of substrate material, and ambient temperature. UCR tags have the capability to track commodities and their temperatures in the supply chain. The area of UCR tag is comparable to regular quick response (QR) code. Experimental results based on UCR tag prototypes have verified their uniqueness and reliability.

The Internet of Things (IoT), an emerging global network of uniquely identifiable embedded computing devices within the existing Internet infrastructure, is transforming how we live and work by increasing the connectedness of people and things on a scale that was once unimaginable. In addition to facilitated information and service exchange between connected objects, enhanced computing power and analytic capabilities of individual objects, and increased interaction between objects and their environments, the IoT also raises new security and privacy challenges. Hardware trust across the IoT supply chain is the foundation of IoT security and privacy. Two major supply chain issues—disappearance/theft of authentic IoT devices and appearance of inauthentic ones—have to be addressed to secure the IoT supply chain and lay the foundation for further security and privacy-defensive measures. Comprehensive solutions that enable IoT device authentication and traceability across the entire supply chain (i.e., during distribution and after being provisioned) need to be established. Existing hardware, software, and network protection methods, however, do not address IoT supply chain issues. To mitigate this shortcoming, we propose an RFID-enabled solution called ReSC that aims at defending the IoT supply chain. By incorporating three techniques—one-to-one mapping between RFID tag identity and control chip identity; unique tag trace, which records tag provenance and history information; and neighborhood attestation of IoT devices—ReSC is resistant to split attacks (i.e., separating tag from product, swapping tags), counterfeit injection, product theft throughout the entire supply chain, device recycling, and illegal network service access (e.g., Internet, cable TV, online games, remote firmware updates). Simulations, theoretical analysis, and experimental results based on a printed circuit board (PCB) prototype demonstrate the effectiveness of ReSC. Finally, we evaluate the security of our proposed scheme against various attacks.

The pharmaceutical supply chain is the pathway through which prescription and over-the-counter (OTC) drugs are delivered from manufacturing sites to patients. Technological innovations, price fluctuations of raw materials, as well as tax, regulatory, and market demands are driving change and making the pharmaceutical supply chain more complex. Traditional supply chain management methods struggle to protect the pharmaceutical supply chain, maintain its integrity, enhance customer confidence, and aid regulators in tracking medicines. To develop effective measures that secure the pharmaceutical supply chain, it is important that the community is aware of the state-of-the-art capabilities available to the supply chain owners and participants. In this article, we will be presenting a survey of existing hardware-enabled pharmaceutical supply chain security schemes and their limitations. We also highlight the current challenges and point out future research directions. This survey should be of interest to government agencies, pharmaceutical companies, hospitals and pharmacies, and all others involved in the provenance and authenticity of medicines and the integrity of the pharmaceutical supply chain.

The Internet of Things (IoT) is transforming the way we live and work by increasing the connectedness of people and things on a scale that was once unimaginable. However, the vulnerabilities in the IoT supply chain have raised serious concerns about the security and trustworthiness of IoT devices and components within them. Testing for device provenance, detection of counterfeit integrated circuits (ICs) and systems, and traceability of IoT devices are challenging issues to address. In this article, we develop a novel radio-frequency identification (RFID)-based system suitable for counterfeit detection, traceability, and authentication in the IoT supply chain called CDTA . CDTA is composed of different types of on-chip sensors and in-system structures that collect necessary information to detect multiple counterfeit IC types (recycled, cloned, etc.), track and trace IoT devices, and verify the overall system authenticity. Central to CDTA is an RFID tag employed as storage and a channel to read the information from different types of chips on the printed circuit board (PCB) in both power-on and power-off scenarios. CDTA sensor data can also be sent to the remote server for authentication via an encrypted Ethernet channel when the IoT device is deployed in the field. A novel board ID generator is implemented by combining outputs of physical unclonable functions (PUFs) embedded in the RFID tag and different chips on the PCB. A light-weight RFID protocol is proposed to enable mutual authentication between RFID readers and tags. We also implement a secure interchip communication on the PCB. Simulations and experimental results using Spartan 3E FPGAs demonstrate the effectiveness of this system. The efficiency of the radio-frequency (RF) communication has also been verified via a PCB prototype with a printed slot antenna.

A finite state machine (FSM) is responsible for controlling the overall functionality of most digital systems and, therefore, the security of the whole system can be compromised if there are vulnerabilities in the FSM. These vulnerabilities can be created by improper designs or by the synthesis tool which introduces additional don't-care states and transitions during the optimization and synthesis process. An attacker can utilize these vulnerabilities to perform fault injection attacks or insert malicious hardware modifications (Trojan) to gain unauthorized access to some specific states. To our knowledge, no systematic approaches have been proposed to analyze these vulnerabilities in FSM. In this paper, we develop a framework named Analyzing Vulnerabilities in FSM (AVFSM) which extracts the state transition graph (including the don't-care states and transitions) from a gate-level netlist using a novel Automatic Test Pattern Generation (ATPG) based approach and quantifies the vulnerabilities of the design to fault injection and hardware Trojan insertion. We demonstrate the applicability of the AVFSM framework by analyzing the vulnerabilities in the FSM of AES and RSA encryption module. We also propose a low-cost mitigation technique to make FSM more secure against these attacks.

The Internet of Things (IoT), an emerging global network of uniquely identifiable embedded computing devices within the existing Internet infrastructure, is transforming how we live and work by increasing the connectedness of people and things on a scale that was once unimaginable. In addition to increased communication efficiency between connected objects, the IoT also brings new security and privacy challenges. Comprehensive measures that enable IoT device authentication and secure access control need to be established. Existing hardware, software, and network protection methods, however, are designed against fraction of real security issues and lack the capability to trace the provenance and history information of IoT devices. To mitigate this shortcoming, we propose an RFID-enabled solution that aims at protecting endpoint devices in IoT supply chain. We take advantage of the connection between RFID tag and control chip in an IoT device to enable data transfer from tag memory to centralized database for authentication once deployed. Finally, we evaluate the security of our proposed scheme against various attacks.