An official website of the United States government
Logic locking has been proposed to safeguard intellectual property (IP) during chip fabrication. Logic locking techniques protect hardware IP by making a subset of combinational modules in a design dependent on a secret key that is withheld from untrusted parties. If an incorrect secret key is used, a set of deterministic errors is produced in locked modules, restricting unauthorized use. A common target for logic locking is neural accelerators, especially as machine-learning-as-a-service becomes more prevalent. In this work, we explore how logic locking can be used to compromise the security of a neural accelerator it protects. Specifically, we show how the deterministic errors caused by incorrect keys can be harnessed to produce neural-trojan-style backdoors. To do so, we first outline a motivational attack scenario where a carefully chosen incorrect key, which we call a trojan key, produces misclassifications for an attacker-specified input class in a locked accelerator. We then develop a theoretically-robust attack methodology to automatically identify trojan keys. To evaluate this attack, we launch it on several locked accelerators. In our largest benchmark accelerator, our attack identified a trojan key that caused a 74% decrease in classification accuracy for attacker-specified trigger inputs, while degrading accuracy by only 1.7% for other inputs on average.
more »
« less
Evaluating the Security of Logic Locking on Deep Neural Networks
Deep neural networks are susceptible to model piracy and adversarial attacks when malicious end-users have full access to the model parameters. Recently, a logic locking scheme called HPNN has been proposed. HPNN utilizes hardware root-of-trust to prevent end-users from accessing the model parameters. This paper investigates whether logic locking is secure on deep neural networks. Specifically, it presents a systematic I/O attack that combines algebraic and learning-based approaches. This attack incrementally extracts key values from the network to minimize sample complexity. Besides, it employs a rigorous procedure to ensure the correctness of the extracted key values. Our experiments demonstrate the accuracy and efficiency of this attack on large networks with complex architectures. Consequently, we conclude that HPNN-style logic locking and its variants we can foresee are insecure on deep neural networks.
more »
« less
- PAR ID:
- 10512031
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM Design Automation Conference
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The development of hardware intellectual properties (IPs) has faced many challenges due to malicious modifications and piracy. One potential solution to protect IPs against these attacks is to perform a key-based logic locking process that disables the functionality and corrupts the output of the IP when the incorrect key value is applied. However, many attacks on logic locking have been introduced to break the locking mechanism and obtain the key. In this paper, we present SWEEP, a constant propagation attack that exploits the change in characteristics of the IP when a single key-bit value is hard-coded. The attack process starts with analyzing design features that are generated from the synthesis tool and establishes a correlation between these features and the correct key values. In order to perform the attack, the logic locking tool needs to be available. The level of accuracy of the extracted key mainly depends on the type of logic locking approach used to obfuscate the IP. Our attack was applied to ISCAS85, and MCNC benchmarks obfuscated using various logic locking techniques and has obtained an average accuracy of 92.09%.more » « less
-
In a zero-trust fabless paradigm, designers are increasingly concerned about hardware-based attacks on the semiconductor supply chain. Logic locking is a design-for-trust method that adds extra key-controlled gates in the circuits to prevent hardware intellectual property theft and overproduction. While attackers have traditionally relied on an oracle to attack logic-locked circuits, machine learning attacks have shown the ability to retrieve the secret key even without access to an oracle. In this paper, we first examine the limitations of state-of-the-art machine learning attacks and argue that the use of key hamming distance as the sole model-guiding structural metric is not always useful. Then, we develop, train, and test a corruptibility-aware graph neural network-based oracle-less attack on logic locking that takes into consideration both the structure and the behavior of the circuits. Our model is explainable in the sense that we analyze what the machine learning model has interpreted in the training process and how it can perform a successful attack. Chip designers may find this information beneficial in securing their designs while avoiding incremental fixes.more » « less
-
Piracy and overproduction of hardware intellectual properties are growing concerns for the semiconductor industry under the fabless paradigm. Although chip designers have attempted to secure their designs against these threats by means of logic locking and obfuscation, due to the increasing number of powerful oracle-guided attacks, they are facing an ever-increasing challenge in evaluating the security of their designs and their associated overhead. Especially while many so-called "provable" logic locking techniques are subjected to a novel attack surface, overcoming these attacks may impose a huge overhead on the circuit. Thus, in this paper, after investigating the shortcoming of state-of-the-art graph neural network models in logic locking and refuting the use of hamming distance as a proper key accuracy metric, we employ two machine learning models, a decision tree to predict the security degree of the locked benchmarks and a convolutional neural network to assign a low-overhead and secure locking scheme to a given circuit. We first build multi-label datasets by running different attacks on locked benchmarks with existing logic locking methods to evaluate the security and compute the imposed area overhead. Then, we design and train a decision tree model to learn the features of the created dataset and predict the security degree of each given locked circuit. Furthermore, we utilize a convolutional neural network model to extract more features, obtain higher accuracy, and consider overhead. Then, we put our trained models to the test against different unseen benchmarks. The experimental results reveal that the convolutional neural network model has a higher capability for extracting features from unseen, large datasets which comes in handy in assigning secure and low-overhead logic locking to a given netlist.more » « less
-
null (Ed.)Logic locking has been widely evaluated as a proactive countermeasure against the hardware security threats within the IC supply chain. However, the introduction of the SAT attack, and many of its derivatives, has raised big concern about this form of countermeasure. In this paper, we explore the possibility of exploiting chaos computing as a new means of logic locking. We introduce the concept of chaotic logic locking, called ChaoLock, in which, by leveraging asymmetric inputs in digital chaotic Boolean gates, we define the concept of programmability (key-configurability) to the sets of underlying initial conditions and system parameters. These initial conditions and system parameters determine the operation (functionality) of each digital chaotic Boolean gate. Also, by proposing dummy inputs in chaotic Boolean gates, we show that during reverse-engineering, the dummy inputs conceal the main functionality of the chaotic Boolean gates, which make the reverse-engineering almost impossible. By performing a security analysis of ChaoLock, we show that with no restriction on conventional CMOS-based ASIC implementation and with no test/debug compromising, none of the state-of-the-art attacks on logic locking, including the SAT attack, could reformulate chaotic Boolean gates while dummy inputs are involved and their parameters are locked. Our analysis and experimental results show that with a low number of chaotic Boolean gates mixed with CMOS digital gates, ChaoLock can guarantee resiliency against the state-of-the-art attacks on logic locking at low overhead.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
