The susceptibility of many strong Physically Unclonable Functions (PUFs) to machine learning (ML)-based modeling attacks is a significant challenge in hardware security. To evaluate the predictability of a PUF, the Hamming Distance Test (HDT) was introduced to measure the probability of output transitions. Poorer HDT values indicate that the attacker can predict some responses better than random guessing. However, existing work has not fully explored the integration of the HDT property for enhancing ML attacks. This paper proposes a chosen challenge strategy combining the HDT property with ML algorithms. The proposed strategy, the Differential Chosen Challenge Attack (DCCA), efficiently models a PUF by forcing the ML algorithm to learn from output transitions. Experimental results show at most 50% of Challenge-Response Paris (CRPs) are reduced compared with conventional ML attacks when attacking XOR Arbiter PUFs (XOR APUF) and Interpose PUFs (IPUFs). Furthermore, the proposed method efficiently learns the XOR trigger-based Adversarial APUFs (AAPUF) that conventional ML attacks are hard to model.

Physically unclonable functions (PUFs) have been widely proposed as hardware primitives for device identification and cryptographic key generation. While strong PUFs provide an exponential number of challenge–response pairs (CRPs) for device authentication, most are vulnerable to machine-learning (ML)-based modeling attacks. Regarding the inherent hard learning problem, adversarial-based PUFs pseudo-randomly switch between several predefined internal states to poison the ML algorithms. However, existing adversarial-based PUFs sacrifice reliability or security against ML attacks. Furthermore, most works only evaluated the ML resistance by empirical experiments, which provides limited evidence for ML resistance. This work explored a novel adversarial-based PUF, Configurable Poisoning PUF (CP PUF), that simultaneously maintains reliability and protects the internal state by a reliability trapdoor. We then connect the proposed CP PUF with the learning parity with noise (LPN) problem to provide a theoretical security guarantee. Experiments show that the reliability of our proposed CP PUF keeps at least 88.9% and outperforms the existing adversarial-based PUFs under different levels of noisy environments. Moreover, the proposed CP PUF achieved a 50.16% accuracy under empirical ML attacks, a near-optimal performance.

Due to the advances in deep reinforcement learning and the demand of large training data, virtual-to-real learning has gained lots of attention from computer vision community recently. As state-of-the-art 3D engines can generate photo-realistic images suitable for training deep neural networks, researchers have been gradually applied 3D virtual environment to learn different tasks including autonomous driving, collision avoidance, and image segmentation, to name a few. Although there are already many open-source simulation environments readily available, most of them either provide small scenes or have limited interactions with objects in the environment. To facilitate visual recognition learning, we present a new Virtual Environment for Visual Deep Learning (VIVID), which offers large-scale diversified indoor and outdoor scenes. Moreover, VIVID leverages the advanced human skeleton system, which enables us to simulate numerous complex human actions. VIVID has a wide range of applications and can be used for learning indoor navigation, action recognition, event detection, etc. We also release several deep learning examples in Python to demonstrate the capabilities and advantages of our system.