Trojan Attacks Research Articles

Detecting Remote Access Trojan (RAT) Attacks based on Different LAN Analysis Methods

Detecting Remote Access Trojan (RAT) Attacks based on Different LAN Analysis Methods

Aggregation-based obfuscation method for electronic systems design

Hardware Trojan attacks relate to malicious modifications of integrated circuits during design or manufacturing, involving untrusted design tools or components. Such modifications can lead to undesired behavior of integrated circuits or the appearance of hidden data leakage channels. There are various methods of classification, detection and prevention of hardware Trojans insertion. One approach to prevent of Trojans insertion is an obfuscation-based design approach. This approach is based on hiding the functional and structural properties of the design, which makes it difficult for an attacker to insert Trojans. The subject matter of research is an aggregation-based obfuscation method for electronic systems design. The goal of the work is to study the process of aggregation-based obfuscation of the electronic systems design. The main idea is that the development and connection phase of the reference monitor is performed in a trusted environment. Thus, an attacker will not be able to obtain its functionality and original structure. The relevance of the work lies in the fact that this approach prevents the possibility of functioning of hardware Trojans. The following tasks were solved in the work: development and study of an aggregation-based obfuscation algorithm for electronic systems design; implementation of the reference monitor presentation as a separate subsystem associated with the main design; experimental evaluation of the possibilities of the method. As a result of the work the aggregation-based obfuscation method for electronic systems design was demonstrated; reference monitor was presented as a separate subsystem associated with the main design; experimental evaluation of the possibilities of the method was demonstrated. The studies allow us to conclude: the obfuscation-based design approach is that the integrated circuit is modified, thus, the functional and structural properties of the design are hidden, which makes it difficult for an attacker to insert Trojans. Aggregation-based obfuscation considers the reference monitor as a separate subsystem associated with the main design.

Neural-network-based hardware trojan attack prediction and security defense mechanism in optical networks-on-chip

Optical networks-on-chip (ONoCs) have emerged as a compelling platform for many-core systems owing to their notable attributes, including high bandwidth, low latency, and energy efficiency. Nonetheless, the integration of microring resonators (MRs) in ONoCs exposes them to vulnerabilities associated with hardware trojans (HTs). In response, we propose an innovative strategy that combines deep-learning-based HT attack prediction with a robust security defense mechanism to fortify the resilience of ONoCs. For HT attack prediction, we employ a multiple-inputs and multiple-outputs long short-term memory neural network model. This model serves to identify susceptible MRs by forecasting alterations in traffic patterns and detecting internal faults within optical routing nodes. On the defensive front, we introduce a fine-grained defense mechanism based on MR faults. This mechanism effectively thwarts HTs during the optical routing process, thereby optimizing node utilization in ONoCs while concurrently upholding security and reliability. Simulation outcomes underscore the efficacy of the proposed HT attack prediction mechanism, demonstrating high accuracy with a loss rate of less than 0.7%. The measured mean absolute error and root mean squared error stand at 0.045 and 0.07, respectively. Furthermore, when compared to conventional coarse-grained node-based defense algorithms, our solution achieves noteworthy reductions of up to 16.2%, 43.72%, and 44.86% in packet loss rate, insertion loss, and crosstalk noise, respectively.

A Novel Two-Level Protection Scheme against Hardware Trojans on a Reconfigurable CNN Accelerator

With the boom in artificial intelligence (AI), numerous reconfigurable convolution neural network (CNN) accelerators have emerged within both industry and academia, aiming to enhance AI computing capabilities. However, this rapid landscape has also witnessed a rise in hardware Trojan attacks targeted at CNN accelerators, thereby posing substantial threats to the reliability and security of these reconfigurable systems. Despite this escalating concern, there exists a scarcity of security protection schemes explicitly tailored to counteract hardware Trojans embedded in reconfigurable CNN accelerators, and those that do exist exhibit notable deficiencies. Addressing these gaps, this paper introduces a dedicated security scheme designed to mitigate the vulnerabilities associated with hardware Trojans implanted in reconfigurable CNN accelerators. The proposed security protection scheme operates at two distinct levels: the first level is geared towards preventing the triggering of the hardware Trojan, while the second level focuses on detecting the presence of a hardware Trojan post-triggering and subsequently neutralizing its potential harm. Through experimental evaluation, our results demonstrate that this two-level protection scheme is capable of mitigating at least 99.88% of the harm cause by three different types of hardware Trojan (i.e., Trojan within RI, MAC and ReLU) within reconfigurable CNN accelerators. Furthermore, this scheme can prevent hardware Trojans from triggering whose trigger signal is derived from a processing element (PE). Notably, the proposed scheme is implemented and validated on a Xilinx Zynq XC7Z100 platform.

Revisiting Black-Hat HLS: A Lightweight Countermeasure to HLS-Aided Trojan Attack

Revisiting Black-Hat HLS: A Lightweight Countermeasure to HLS-Aided Trojan Attack

An Adaptive Black-Box Defense Against Trojan Attacks (TrojDef).

Trojan backdoor is a poisoning attack against neural network (NN) classifiers in which adversaries try to exploit the (highly desirable) model reuse property to implant Trojans into model parameters for backdoor breaches through a poisoned training process. To misclassify an input to a target class, the attacker activates the backdoor by augmenting the input with a predefined trigger that is only known to her/him. Most of the proposed defenses against Trojan attacks assume a white-box setup, in which the defender either has access to the inner state of NN or is able to run backpropagation through it. In this work, we propose a more practical black-box defense, dubbed TrojDef. In a black-box setup, the defender can only run forward-pass of the NN. TrojDef is motivated by the Trojan poisoned training, in which the model is trained on both benign and Trojan inputs. TrojDef tries to identify and filter out Trojan inputs (i.e., inputs augmented with the Trojan trigger) by monitoring the changes in the prediction confidence when the input is repeatedly perturbed by random noise. We derive a function based on the prediction outputs which is called the prediction confidence bound to decide whether the input example is Trojan or not. The intuition is that Trojan inputs are more stable as the misclassification only depends on the trigger, while benign inputs will suffer when augmented with noise due to the perturbation of the classification features. Through mathematical analysis, we show that if the attacker is perfect in injecting the backdoor, the Trojan infected model will be trained to learn the appropriate prediction confidence bound, which is used to distinguish Trojan and benign inputs under arbitrary perturbations. However, because the attacker might not be perfect in injecting the backdoor, we introduce a nonlinear transform to the prediction confidence bound to improve the detection accuracy in practical settings. Extensive empirical evaluations show that TrojDef significantly outperforms the-state-of-the-art defenses and is highly stable under different settings, even when the classifier architecture, the training process, or the hyperparameters change.

Coherence Attacks and Countermeasures in Interposer-based Chiplet Systems

Industry is moving towards large-scale hardware systems that bundle processor cores, memories, accelerators, and so on. via 2.5D integration. These components are fabricated separately as chiplets and then integrated using an interposer as an interconnect carrier. This new design style is beneficial in terms of yield and economies of scale, as chiplets may come from various vendors and are relatively easy to integrate into one larger sophisticated system. However, the benefits of this approach come at the cost of new security challenges, especially when integrating chiplets that come from untrusted or not fully trusted, third- party vendors. In this work, we explore these challenges for modern interposer-based systems of cache-coherent, multi-core chiplets. First, we present basic coherence-oriented hardware Trojan attacks that pose a significant threat to chiplet-based designs and demonstrate how these basic attacks can be orchestrated to pose a significant threat to interposer-based systems. Second, we propose a novel scheme using an active interposer as a generic, secure-by-construction platform that forms a physical root of trust for modern 2.5D systems. The implementation of our scheme is confined to the interposer, resulting in little cost and leaving the chiplets and coherence system untouched. We show that our scheme prevents a range of coherence attacks with low overheads on system performance, ∼4%. Further, we demonstrate that our scheme scales efficiently as system size and memory capacities increase, resulting in reduced performance overheads.

Hardware Trojan Attacks on the Reconfigurable Interconnections of Field-Programmable Gate Array-Based Convolutional Neural Network Accelerators and a Physically Unclonable Function-Based Countermeasure Detection Technique.

Convolutional neural networks (CNNs) have demonstrated significant superiority in modern artificial intelligence (AI) applications. To accelerate the inference process of CNNs, reconfigurable CNN accelerators that support diverse networks are widely employed for AI systems. Given the ubiquitous deployment of these AI systems, there is a growing concern regarding the security of CNN accelerators and the potential attacks they may face, including hardware Trojans. This paper proposes a hardware Trojan designed to attack a crucial component of FPGA-based CNN accelerators: the reconfigurable interconnection network. Specifically, the hardware Trojan alters the data paths during activation, resulting in incorrect connections in the arithmetic circuit and consequently causing erroneous convolutional computations. To address this issue, the paper introduces a novel detection technique based on physically unclonable functions (PUFs) to safeguard the reconfigurable interconnection network against hardware Trojan attacks. Experimental results demonstrate that by incorporating a mere 0.27% hardware overhead to the accelerator, the proposed hardware Trojan can degrade the inference accuracy of popular neural network architectures, including LeNet, AlexNet, and VGG, by a significant range of 8.93% to 86.20%. The implemented arbiter-PUF circuit on a Xilinx Zynq XC7Z100 platform successfully detects the presence and location of hardware Trojans in a reconfigurable interconnection network. This research highlights the vulnerability of reconfigurable CNN accelerators to hardware Trojan attacks and proposes a promising detection technique to mitigate potential security risks. The findings underscore the importance of addressing hardware security concerns in the design and deployment of AI systems utilizing FPGA-based CNN accelerators.

Circular semi-quantum secret sharing based on hybrid single particle and GHZ-type states

Semi-quantum secret sharing (SQSS) is a branch of quantum cryptography, with the advantage of fewer quantum resources. In this paper, we present a SQSS protocol based on hybrid single particle and GHZ-type states. Our protocol adopts circular transport structure to share secret information between classical and quantum parties, employing the entanglement correlation and uncertainty of GHZ-type states to guarantee the security of the transmission. Security analysis indicates that the proposed SQSS protocol enables resilience against various potential attacks such as measure-resend, entangle-measure, internal, and Trojan attacks. Furthermore, our protocol is easy to generalize to multi-party scenarios without increasing the complexity of state preparation. Compared with some typical SQSS protocols, our protocol has higher qubit efficiency without the need for entanglement swapping operations. The proposed SQSS protocol has the potential for broader applications in practical scenarios.

Research and Development Priorities for Security of Embedded Hardware Devices

Supply chains for embedded hardware devices are subject to a variety of security threats that are concerning to governments and industry. Such threats include counterfeit parts, cyber-attacks, Trojan attacks, reliance on offshore-manufactured and controlled hardware, software, and rapid increase of network technologies. Addressing these threats is vital to maintain and enhance system trust and security. This article develops a framework to address initiatives and success criteria which accounts for different perspectives of system stakeholders and identify different potential emergent conditions and scenarios which are most and least impactful to the trust and security of the supply chain. The article demonstrates a research and development priorities preferences method that accounts for evolving perspectives of supply chain stakeholders and describing the example application of embedded hardware devices as a system.

AI Trojan Attack for Evading Machine Learning-based Detection of Hardware Trojans

The globalized semiconductor supply chain significantly increases the risk of exposing System-on-Chip (SoC) designs to hardware Trojans. While machine learning (ML) based Trojan detection approaches are promising due to their scalability as well as detection accuracy, ML-based methods themselves are vulnerable from Trojan attacks. In this paper, we propose a robust backdoor attack on ML-based Trojan detection algorithms to demonstrate this serious vulnerability. The proposed framework is able to design an AI Trojan and implant it inside the ML model that can be triggered by specific inputs. Experimental results demonstrate that the proposed AI Trojans can bypass state-of-the-art defense algorithms. Moreover, our approach provides a fast and cost-effective solution in achieving 100% attack success rate that outperforms state-of-the art methods based on adversarial attacks.

Securing One-Class Federated Learning Classifiers Against Trojan Attacks in Smart Grid

Securing One-Class Federated Learning Classifiers Against Trojan Attacks in Smart Grid

Trojan Attack and Defense for Deep Learning-Based Navigation Systems of Unmanned Aerial Vehicles

Trojan Attack and Defense for Deep Learning-Based Navigation Systems of Unmanned Aerial Vehicles

Imperceptible Trojan Attacks to the Graph-based Big Data Processing in Smart Society

Imperceptible Trojan Attacks to the Graph-based Big Data Processing in Smart Society

Identification of Hardware Trojan in Gate-Level Netlist

Hardware Trojans (HT) are tiny, malicious circuits intentionally designed by an adversary. The existing works found in the literature on gate-level netlists are mainly based on supervised classification with few attempts at unsupervised clustering. However, the over-reliance on pre-defined structural features used in these supervised classification methods makes them vulnerable to the new Trojan attacks, whereas most unsupervised methods ignore this feature completely. This work presents an unsupervised approach for HT net detection based on the structural features required for small rare-event triggered HTs irrespective of the payload. The proposed work uses k-means clustering on these features to reduce the search space. A new metric based on combinational controllability is applied next to detect the possible trigger net. Experimental results of fifteen selected Trust-HUB benchmarks show the capability of the proposed technique against different types of HT triggers. Results show that the proposed approach reduces the search space massively (up to 99%) while running within a reasonable time frame.

APTSHIELD: A Stable, Efficient and Real-Time APT Detection System for Linux Hosts

Advanced Persistent Threat (APT) attack usually refers to the form of long-term, covert and sustained attack on specific targets, with an adversary using advanced attack techniques to destroy the key facilities of an organization. APT attacks have caused serious security threats and massive financial loss worldwide. Academics and industry thereby have proposed a series of solutions to detect APT attacks, such as dynamic/static code analysis, traffic detection, sandbox technology, endpoint detection and response (EDR), etc. However, existing defenses are failed to accurately and effectively defend against the current APT attacks that exhibit strong persistent, stealthy, diverse and dynamic characteristics due to the weak data source integrity, large data processing overhead and poor real-time performance in the process of real-world scenarios. To overcome these difficulties, in this paper we propose APTSHIELD, a stable, efficient and real-time APT detection system for Linux hosts. In the aspect of data collection, audit is selected to stably collect kernel data of the operating system so as to carry out a complete portrait of the attack based on comprehensive analysis and comparison of existing logging tools; In the aspect of data processing, redundant semantics skipping and non-viable node pruning are adopted to reduce the amount of data, so as to reduce the overhead of the detection system; In the aspect of attack detection, an APT attack detection framework based on ATT&CK model is designed to carry out real-time attack response and alarm through the transfer and aggregation of labels. Experimental results on both laboratory and Darpa Engagement show that our system can effectively detect web vulnerability attacks, file-less attacks and remote access trojan attacks, and has a low false positive rate, which adds far more value than the existing frontier work.

SGBA: A stealthy scapegoat backdoor attack against deep neural networks

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled correctly while those carrying a specific trigger are falsely given a target label. Due to the severity of such attacks, many backdoor detection and containment systems have recently, been proposed for deep neural networks. One major category among them are various model inspection schemes, which hope to detect backdoors before deploying models from non-trusted third-parties. In this paper, we show that such state-of-the-art schemes can be defeated by a so-called Scapegoat Backdoor Attack, which introduces a benign scapegoat trigger in data poisoning to prevent the defender from reversing the real abnormal trigger. In addition, it confines the values of network parameters within the same variances of those from clean model during training, which further significantly enhances the difficulty of the defender to learn the differences between legal and illegal models through machine-learning approaches. Our experiments on 3 popular datasets show that it can escape detection by all five state-of-the-art model inspection schemes. Moreover, this attack brings almost no side-effects on the attack effectiveness and guarantees the universal feature of the trigger compared with original patch-based trojan attacks.

A Framework for Automated Exploration of Trojan Attack Space in FPGA Netlists

Field Programmable Gate Arrays (FPGAs) provide a flexible compute platform for quick prototyping or hardware acceleration in diverse application domains. However, similar to the global semiconductor life-cycle in the modern supply chain, FPGA-based product development includes processes and interactions with potentially untrusted parties outside the traditional scrutiny of a completely in-house development cycle. An untrusted party or software can maliciously alter a hardware intellectual property (IP) block mapped to an FPGA device during various stages of the FPGA life-cycle. Such malicious alterations, also known as hardware Trojan attacks, have garnered significant research into their detection and prevention in the context of application-specific integrated circuit (ASIC) design flow. However, Trojan attacks in FPGAs have not enjoyed this same attention. Designers often rely on mapping ASIC-specific solutions and evaluation benchmarks to the FPGA domain, which leaves much of the FPGA-specific Trojan space uncovered. We note that the distinctive business model as well as the architectural configurations of FPGAs present unique opportunities for Trojan attacks to an adversary. To this end, we introduce a framework to automatically explore the hardware Trojan attack space in FPGA netlists. It is capable of inserting different types of FPGA-specific Trojans in a netlist enabling rapid exploration of potential Trojan attacks in an FPGA design: soft-template, monolithic, and distributed dark silicon. Soft template Trojans use behavioral templates with random synthesis constraints to increase Trojan structural diversity. Monolithic and distributed dark silicon Trojans use the under-utilized input space (FPGA dark silicon) in FPGA primitives to realize Trojans with effectively zero area and power footprint. Further optimizations are also presented to remove any potential delay impact. We then generate over 1300 Trojan-inserted benchmarks using each of the introduced FPGA Trojan classes, and compare their impact on utilization, delay, and power. Finally, we evaluate our Trojans against a machine learning-based Trojan detection to highlight their evasiveness.

Leaking Wireless ICs via Hardware Trojan-Infected Synchronization

We propose a Hardware Trojan (HT) attack in wireless Integrated Circuits (ICs) that aims at leaking sensitive information within a legitimate transmission. The HT is hidden inside the transmitter modulating the sensitive information into the preamble of each transmitted frame which is used for the synchronization of the transmitter with the receiver. The data leakage does not affect synchronization and is imperceptible by the inconspicuous nominal receiver as it does not incur any performance penalty in the communication. A knowledgeable rogue receiver, however, can recover the data using signal processing that is too expensive and impractical to be used during run-time in nominal receivers. The HT mechanism is designed at circuit-level and is embedded entirely into the digital section of the RF transceiver having a tiny footprint. The proposed HT attack is demonstrated with measurements on a hardware platform. We demonstrate the stealthiness of the attack, i.e., its ability to evade defenses based on testing and run-time monitoring, and the robustness of the attack, i.e., the ability of the rogue receiver to recover the leaked information even under unfavorable channel conditions.

Defending Your Mobile Fortress: An In-Depth Look at on-Device Trojan Detection in Machine Learning: Systematic Literature Review

Mobile app trojans are becoming an increasingly serious threat to personal information security. They can cause severe damage by exposing sensitive and personally-identifying information to malicious actors. This paper’s contribution is a comprehensive review of the attack vectors for trojan attacks, and ways to eliminate the risks posed by attack vectors and generate settlement automatically. As such, such attacks must be prevented. In this study, we explore to find how to detect the trojan attack in detail, and the way that we know in machine learning. A review is conducted on the state-of-the-art methods using the preferred reporting items for reviews and meta-analyses (PRISMA) guidelines. We review literature from several publications and analyze the use of machine learning for on-device trojan detection. This review provides evidence for the effectiveness of machine learning in detecting such threats. The current trend shows that signature-based analysis using various metadata, such as permission, intent, API and system calls, and network analysis, are capable of detecting trojan attacks before and after the initial infection