This supplementary material provides the details of the experiment in the paper. We introduce the implementation details and additional ablation studies of 3D detection in this part. The configuration of the GCE PointNet++ is shown in Table 1. The numbers are explained as follows. These parameters are inherited from SA layers.

Global context is crucial for 3D point cloud scene understanding tasks.

This supplementary material provides the details of the experiment in the paper. We introduce the implementation details and additional ablation studies of 3D detection in this part. The configuration of the GCE PointNet++ is shown in Table 1. The numbers are explained as follows. These parameters are inherited from SA layers.

Global context is crucial for 3D point cloud scene understanding tasks.

Global context is crucial for 3D point cloud scene understanding tasks. In this work, we extended the contextual encoding layer that was originally designed for 2D tasks to 3D Point Cloud scenarios. The encoding layer learns a set of code words in the feature space of the 3D point cloud to characterize the global semantic context, and then based on these code words, the method learns a global contextual descriptor to reweight the featuremaps accordingly. Moreover, compared to 2D scenarios, data sparsity becomes a major issue in 3D point cloud scenarios, and the performance of contextual encoding quickly saturates when the number of code words increases. To mitigate this problem, we further proposed a group contextual encoding method, which divides the channel into groups and then performs encoding on group-divided feature vectors.

Never before has it been easier to clone a human voice. New AI tools can take a voice sample, process it, copy it, and say anything in the voice of the original. It's been a thing since as early as 2018, but modern tools can do it faster, more accurately, and with greater ease. OpenAI, the artificial intelligence company behind ChatGPT, presented a project this year that showed how it's possible to clone a voice with nothing more than a 15-second recording. OpenAI's tool isn't yet publicly available and it's said to have security measures in place to prevent misuse.

Covert communication (also known as steganography) is the practice of concealing a secret inside an innocuous-looking public object (cover) so that the modified public object (covert code) makes sense to everyone but only someone who knows the code can extract the secret (message). Linguistic steganography is the practice of encoding a secret message in natural language text such as spoken conversation or short public communications such as tweets.. While ad hoc methods for covert communications in specific domains exist ( JPEG images, Chinese poetry, etc), there is no general model for linguistic steganography specifically. We present a novel mathematical formalism for creating linguistic steganographic codes, with three parameters: Decodability (probability that the receiver of the coded message will decode the cover correctly), density (frequency of code words in a cover code), and detectability (probability that an attacker can tell the difference between an untampered cover compared to its steganized version). Verbal or linguistic steganography is most challenging because of its lack of artifacts to hide the secret message in. We detail a practical construction in Python of a steganographic code for Tweets using inserted words to encode hidden digits while using n-gram frequency distortion as the measure of detectability of the insertions. Using the publicly accessible Stanford Sentiment Analysis dataset we implemented the tweet steganization scheme -- a codeword (an existing word in the data set) inserted in random positions in random existing tweets to find the tweet that has the least possible n-gram distortion. We argue that this approximates KL distance in a localized manner at low cost and thus we get a linguistic steganography scheme that is both formal and practical and permits a tradeoff between codeword density and detectability of the covert message.

Artificial Neural Networks (ANN) have gained large popularity thanks to their ability to learn using the well-known backpropagation algorithm. On the other hand, Spiking Neural Networks (SNNs), despite having wider abilities than ANNs, have always presented a challenge in the training phase. This paper shows a new method to perform supervised learning on SNNs, using Spike Timing Dependent Plasticity (STDP) and homeostasis, aiming at training the network to identify spatial patterns. The method is tested using the SpiNNaker digital architecture. A SNN is trained to recognise one or multiple patterns and performance metrics are extracted to measure the performance of the network. Some considerations are drawn from the results showing that, in the case of a single trained pattern, the network behaves as the ideal detector, with 100% accuracy in detecting the trained pattern. However, as the number of trained patterns on a single network increases, the accuracy of the identification is linked to the similarities between these patterns. This method of training an SNN to detect spatial patterns may be applied on pattern recognition in static images or traffic analysis in computer networks, where each network packet represents a spatial pattern. It will be stipulated that the homeostatic factor may enable the network to detect patterns with some degree of similarities, rather than only perfectly matching patterns.

We consider the well-studied Robust $(k, z)$-Clustering problem, which generalizes the classic $k$-Median, $k$-Means, and $k$-Center problems. Given a constant $z\ge 1$, the input to Robust $(k, z)$-Clustering is a set $P$ of $n$ weighted points in a metric space $(M,\delta)$ and a positive integer $k$. Further, each point belongs to one (or more) of the $m$ many different groups $S_1,S_2,\ldots,S_m$. Our goal is to find a set $X$ of $k$ centers such that $\max_{i \in [m]} \sum_{p \in S_i} w(p) \delta(p,X)^z$ is minimized. This problem arises in the domains of robust optimization [Anthony, Goyal, Gupta, Nagarajan, Math. Oper. Res. 2010] and in algorithmic fairness. For polynomial time computation, an approximation factor of $O(\log m/\log\log m)$ is known [Makarychev, Vakilian, COLT $2021$], which is tight under a plausible complexity assumption even in the line metrics. For FPT time, there is a $(3^z+\epsilon)$-approximation algorithm, which is tight under GAP-ETH [Goyal, Jaiswal, Inf. Proc. Letters, 2023]. Motivated by the tight lower bounds for general discrete metrics, we focus on \emph{geometric} spaces such as the (discrete) high-dimensional Euclidean setting and metrics of low doubling dimension, which play an important role in data analysis applications. First, for a universal constant $\eta_0 >0.0006$, we devise a $3^z(1-\eta_{0})$-factor FPT approximation algorithm for discrete high-dimensional Euclidean spaces thereby bypassing the lower bound for general metrics. We complement this result by showing that even the special case of $k$-Center in dimension $\Theta(\log n)$ is $(\sqrt{3/2}- o(1))$-hard to approximate for FPT algorithms. Finally, we complete the FPT approximation landscape by designing an FPT $(1+\epsilon)$-approximation scheme (EPAS) for the metric of sub-logarithmic doubling dimension.

This month, a local TV-news station in Arizona ran an unsettling report: A mother named Jennifer DeStefano says that she picked up the phone to the sound of her 15-year-old crying out for her, and was asked to pay a $1 million ransom for her daughter's return. In reality, the teen had not been kidnapped, and was safe; DeStefano believes someone used AI to create a replica of her daughter's voice to deploy against her family. "It was completely her voice," she said in one interview. It was the way she would have cried." DeStefano's story has since been picked up by other outlets, while similar stories of AI voice scams have surfaced on TikTok and been reported by The Washington Post.