Search

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples; (ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, \ie, even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at \url{https://github.com/CGCL-codes/UnlearnablePC}, Comment: NeurIPS 2024

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM., Comment: This paper has been accepted by the 38th Annual Conference on Neural Information Processing Systems (NeurIPS'24)

Localization of the craniofacial landmarks from lateral cephalograms is a fundamental task in cephalometric analysis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the "Cephalometric Landmark Detection (CL-Detection)" dataset, which is the largest publicly available and comprehensive dataset for cephalometric landmark detection. This multi-center and multi-vendor dataset includes 600 lateral X-ray images with 38 landmarks acquired with different equipment from three medical centers. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go for cephalometric landmark detection. Following the 2023 MICCAI CL-Detection Challenge, we report the results of the top ten research groups using deep learning methods. Results show that the best methods closely approximate the expert analysis, achieving a mean detection rate of 75.719% and a mean radial error of 1.518 mm. While there is room for improvement, these findings undeniably open the door to highly accurate and fully automatic location of craniofacial landmarks. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for the community to benchmark future algorithm developments at https://cl-detection2023.grand-challenge.org/., Comment: 16 pages, 7 figures

Embodied AI represents systems where AI is integrated into physical entities, enabling them to perceive and interact with their surroundings. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BadRobot, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge's flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BadRobot's attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BadRobot. Warning: This paper contains harmful AI-generated language and aggressive actions., Comment: 38 pages, 16 figures

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, some defense mechanisms have been proposed such as adversarial training, image transformation techniques, and image purification. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then begin by introducing Gaussian noise to absorb the poisons and then apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://github.com/CGCL-codes/ECLIPSE., Comment: Accepted by ESORICS 2024

Black phosphorus nitrogen (BP-N) is an attractive high-energy-density material. However, high-pressure synthesized BP-N will decompose at low-pressure and cannot be quenched to ambient conditions. Finding a method to stabilize it at 0 GPa is of great significance for its practical applications. However, unlike cg-N, LP-N, and HLP-N, it is always a metastable phase at high-pressure up to 260 GPa, and decomposes into chains at 23 GPa. Here, based on the first-principles simulations, we find that P atom doping can effectively reduce the synthesis pressure of BP-N and maintain its stability at 0 GPa. Uniform distribution of P atom dopants within the layer helps maintain the structural stability of BP-N layer at 0 GPa, while interlayer electrostatic interaction induced by N-P dipoles enhances its dynamic stability by eliminating interlayer slipping. Furthermore, pressure is conducive to enhancing the stability of BP-N and its doped forms by suppressing N-chain dissociation. For the configuration with 12.5% doping concentration, a gravimetric energy density of 8.07 kJ/g can be realized, which is nearly two times higher than TNT., Comment: 27 pages, 6 figures

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks., Comment: Accepted to IJCAI 2024

Recently, the Kagome metal CsTi$_3$Bi$_5$ has exhibited several novel quantum properties similar to CsV$_3$Sb$_5$, such as nontrivial topology, double-dome superconductivity, and flat band features. However, CsTi$_3$Bi$_5$ lacks the charge-density wave (CDW) present in CsV$_3$Sb$_5$, making the study of its emergence of double-dome superconductivity a focus of research. In this work, we have identified an order parameter, the three-band Z$_2$ topological index, that can describe the superconducting phase diagram of CsTi$_3$Bi$_5$ under pressure. Its evolution with pressure follows the expected behavior for superconductivity. Furthermore, the results of the Fermi surface under pressure reveal the potential presence of a Lifshitz transition in the vicinity of the vanishing point of the superconducting temperature change with pressure in CsTi$_3$Bi$_5$. These results indicate that the superconducting behavior of CsTi$_3$Bi$_5$ under pressure is caused by changes in the electronic structure leading to alterations in the topological properties, provide new insights and approaches for understanding the superconducting phenomenon in Kagome metals.

Cubic gauche nitrogen (cg-N) has received wide attention due to its high energy density and environmental friendliness. However, existing synthesis methods for cg-N predominantly rely on the high-pressure techniques, or the utilization of nanoconfined effects using highly toxic and sensitive sodium azide as precursor, which significantly restrict the practical application of cg-N as high energy density materials (HDEM). Here, based on the first-principles simulations, we find that the adsorption of potassium on the cg-N surface exhibits superior stabilization compared to sodium. Then, we chose the safer potassium azide as raw material for synthesizing cg-N. Through plasma-enhanced chemical vapor deposition treatment, the free-standing cg-N was successfully synthesized without the need of high-pressure and nanoconfined effects. Importantly, it demonstrates excellent thermal stability up to 760 K, and then a rapid and intense thermal decomposition occurs, exhibiting typical behaviors of HDEM thermal decomposition. Our work has significantly promoted the practical application of cg-N as HDEM.

Unlearnable datasets lead to a drastic drop in the generalization performance of models trained on them by introducing elaborate and imperceptible perturbations into clean training sets. Many existing defenses, e.g., JPEG compression and adversarial training, effectively counter UDs based on norm-constrained additive noise. However, a fire-new type of convolution-based UDs have been proposed and render existing defenses all ineffective, presenting a greater challenge to defenders. To address this, we express the convolution-based unlearnable sample as the result of multiplying a matrix by a clean sample in a simplified scenario, and formalize the intra-class matrix inconsistency as $\Theta_{imi}$, inter-class matrix consistency as $\Theta_{imc}$ to investigate the working mechanism of the convolution-based UDs. We conjecture that increasing both of these metrics will mitigate the unlearnability effect. Through validation experiments that commendably support our hypothesis, we further design a random matrix to boost both $\Theta_{imi}$ and $\Theta_{imc}$, achieving a notable degree of defense effect. Hence, by building upon and extending these facts, we first propose a brand-new image COrruption that employs randomly multiplicative transformation via INterpolation operation to successfully defend against convolution-based UDs. Our approach leverages global pixel random interpolations, effectively suppressing the impact of multiplicative noise in convolution-based UDs. Additionally, we have also designed two new forms of convolution-based UDs, and find that our defense is the most effective against them.

Recently, Lu-N-H materials were reported to have room-temperature superconductivity, and the Hubbard U correction on the Lu's $\textit{f}$-electrons is necessary, and a constant U = 5.5 eV was applied to different Lu-N-H configurations (Nature 615, 244 (2023)). Following simulations indicate that the superconducting transition temperature (T$_{c}$) of LuH$_{3}$ with U = 0 eV is 50 ~ 60 K, while the N-doped LuH$_{3}$ is below 30 K. Quite recently, calculations with U = 5 eV shows that the T$_{c}$ of N-doped LuH$_{3}$ exceeds 100 K. The properties of Lu-N-H are sensitive to the applied U values. Here, the structural and electronic Lu-N-H properties at high-pressure (0 ~ 10 GPa) are systematically investigated based on the hybrid functional. We show that different Lu-N-H configurations should possess different U values varying from 6.4 eV to 7.4 eV. Furthermore, at pressure ranging from 0 GPa to 1 GPa, the $\textit{f}$ and $\textit{d}$ band centers of N-doped LuH$_{3}$ show oscillation or even plateau, and the band gap of insulators also shows a platform near this pressure, this is consistent with the pressure range where room-temperature superconductivity appeared in Lu-N-H. Our work provides insights into the understanding of Lu-N-H materials and other hydrogen-rich superconductors based on the rare-earth elements.

Cubic gauche polynitrogen (cg-N) is an attractive high-energy density material. However, high-pressure synthesized cg-N will decompose at low-pressure and cannot exist at ambient conditions. Here, the stabilities of cg-N surfaces with and without saturations at different pressures and temperatures are investigated systematically. Pristine surfaces at 0 GPa are very brittle and will decompose at 300 K, especially (1 1 0) surface will collapse completely just after structural relaxation, whereas the decompositions of surfaces can be suppressed by applying pressure, indicating that surface instability causes the cg-N decomposition at low-pressure. Due to the saturation of dangling bonds and transferring electrons to the surfaces, saturation with H can stabilize surfaces at ambient conditions, while OH saturation cannot because of getting electrons from the surfaces. An acidic environment or surface saturation with less electronegative adsorbates is more favorable for the stability of polymerized nitrogen., Comment: 21 pages, 5 figures

Based on the hybrid functional, we find that at 0 GPa, the pristine CsV$_{3}$Sb$_{5}$ has local magnetic moment of 0.85 $\mu_B$ /unit cell, which is suppressed at pressure of 2.5 GPa resulting in a spin-crossover. Since the ground sate of CsV$_{3}$Sb$_{5}$ with charge density wave (CDW) distortion is non-magnetic state, the local magnetic moment of pristine CsV$_{3}$Sb$_{5}$ will be suppressed by temperature-induced CDW transition at 94 K. The schematic evolution of magnetic moments as functions of pressure and temperature are presented. At low temperature, CsV$_{3}$Sb$_{5}$ is a rare example of materials hosting pressureinduced local magnetic moment, and we suggeste that the effects of local magnetic moments should be considered for understanding its properties.

High-pressure properties of MnPS$_3$ are investigated by using the hybrid functional, we report a spin-crossover pressure of 35 GPa consisting with experimental observation (30 GPa), less than half of existing report (63 GPa) using the Hubbard U correction. Interestingly, a spin-crossover induced antiferromagnetism-to-ferromagnetism transition combined with stacking-order change from monoclinic to rhombohedral are founded, and the ferromagnetism origins from the partially occupied $t_{2g}$ orbitals. Different from previous understanding, the Mott metal-insulator transition of MnPS$_3$ does not occur simultaneously with the spin-crossover but in pressurized low-spin phase., Comment: 20 pages, 6 figures and 1 table