How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection

Object detection (OD) in computer vision has made significant progress in recent years, transitioning from closed-set labels to open-vocabulary detection (OVD) based on large-scale vision-language pre-training (VLP). However, current evaluation methods and datasets are limited to testing generalization over object types and referral expressions, which do not provide a systematic, fine-grained, and accurate benchmark of OVD models' abilities. In this paper, we propose a new benchmark named OVDEval, which includes 9 sub-tasks and introduces evaluations on commonsense knowledge, attribute understanding, position understanding, object relation comprehension, and more. The dataset is meticulously created to provide hard negatives that challenge models' true understanding of visual and linguistic input. Additionally, we identify a problem with the popular Average Precision (AP) metric when benchmarking models on these fine-grained label datasets and propose a new metric called Non-Maximum Suppression Average Precision (NMS-AP) to address this issue. Extensive experimental results show that existing top OVD models all fail on the new tasks except for simple object types, demonstrating the value of the proposed dataset in pinpointing the weakness of current OVD models and guiding future research. Furthermore, the proposed NMS-AP metric is verified by experiments to provide a much more truthful evaluation of OVD models, whereas traditional AP metrics yield deceptive results. Data is available at \url{https://github.com/om-ai-lab/OVDEval}

IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse

Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task. Transfer RL methods can reshape the policy optimization objective (optimization transfer) or influence the behavior policy (behavior transfer) using source policies. However, selecting the appropriate source policy with limited samples to guide target policy learning has been a challenge. Previous methods introduce additional components, such as hierarchical policies or estimations of source policies' value functions, which can lead to non-stationary policy optimization or heavy sampling costs, diminishing transfer effectiveness. To address this challenge, we propose a novel transfer RL method that selects the source policy without training extra components. Our method utilizes the Q function in the actor-critic framework to guide policy selection, choosing the source policy with the largest one-step improvement over the current target policy. We integrate optimization transfer and behavior transfer (IOB) by regularizing the learned policy to mimic the guidance policy and combining them as the behavior policy. This integration significantly enhances transfer effectiveness, surpasses state-of-the-art transfer RL baselines in benchmark tasks, and improves final performance and knowledge transferability in continual learning scenarios. Additionally, we show that our optimization transfer technique is guaranteed to improve target policy learning.

ChatGPT for Software Security: Exploring the Strengths and Limitations of ChatGPT in the Security Applications

ChatGPT, as a versatile large language model, has demonstrated remarkable potential in addressing inquiries across various domains. Its ability to analyze, comprehend, and synthesize information from both online sources and user inputs has garnered significant attention. Previous research has explored ChatGPT's competence in code generation and code reviews. In this paper, we delve into ChatGPT's capabilities in security-oriented program analysis, focusing on perspectives from both attackers and security analysts. We present a case study involving several security-oriented program analysis tasks while deliberately introducing challenges to assess ChatGPT's responses. Through an examination of the quality of answers provided by ChatGPT, we gain a clearer understanding of its strengths and limitations in the realm of security-oriented program analysis.

Double-chain Constraints for 3D Human Pose Estimation in Images and Videos

Reconstructing 3D poses from 2D poses lacking depth information is particularly challenging due to the complexity and diversity of human motion. The key is to effectively model the spatial constraints between joints to leverage their inherent dependencies. Thus, we propose a novel model, called Double-chain Graph Convolutional Transformer (DC-GCT), to constrain the pose through a double-chain design consisting of local-to-global and global-to-local chains to obtain a complex representation more suitable for the current human pose. Specifically, we combine the advantages of GCN and Transformer and design a Local Constraint Module (LCM) based on GCN and a Global Constraint Module (GCM) based on self-attention mechanism as well as a Feature Interaction Module (FIM). The proposed method fully captures the multi-level dependencies between human body joints to optimize the modeling capability of the model. Moreover, we propose a method to use temporal information into the single-frame model by guiding the video sequence embedding through the joint embedding of the target frame, with negligible increase in computational cost. Experimental results demonstrate that DC-GCT achieves state-of-the-art performance on two challenging datasets (Human3.6M and MPI-INF-3DHP). Notably, our model achieves state-of-the-art performance on all action categories in the Human3.6M dataset using detected 2D poses from CPN, and our code is available at: https://github.com/KHB1698/DC-GCT.

Sensing Aided Covert Communications: Turning Interference into Allies

In this paper, we investigate the realization of covert communication in a general radar-communication cooperation system, which includes integrated sensing and communications as a special example. We explore the possibility of utilizing the sensing ability of radar to track and jam the aerial adversary target attempting to detect the transmission. Based on the echoes from the target, the extended Kalman filtering technique is employed to predict its trajectory as well as the corresponding channels. Depending on the maneuvering altitude of adversary target, two channel models are considered, with the aim of maximizing the covert transmission rate by jointly designing the radar waveform and communication transmit beamforming vector based on the constructed channels. For the free-space propagation model, by decoupling the joint design, we propose an efficient algorithm to guarantee that the target cannot detect the transmission. For the Rician fading model, since the multi-path components cannot be estimated, a robust joint transmission scheme is proposed based on the property of the Kullback-Leibler divergence. The convergence behaviour, tracking MSE, false alarm and missed detection probabilities, and covert transmission rate are evaluated. Simulation results show that the proposed algorithms achieve accurate tracking. For both channel models, the proposed sensing-assisted covert transmission design is able to guarantee the covertness, and significantly outperforms the conventional schemes.

SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark

Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. However, it has been increasingly recognized that the "comparing different MI attacks" methodology used in the existing works has serious limitations. Due to these limitations, we found (through the experiments in this work) that some comparison results reported in the literature are quite misleading. In this paper, we seek to develop a comprehensive benchmark for comparing different MI attacks, called MIBench, which consists not only the evaluation metrics, but also the evaluation scenarios. And we design the evaluation scenarios from four perspectives: the distance distribution of data samples in the target dataset, the distance between data samples of the target dataset, the differential distance between two datasets (i.e., the target dataset and a generated dataset with only nonmembers), and the ratio of the samples that are made no inferences by an MI attack. The evaluation metrics consist of ten typical evaluation metrics. We have identified three principles for the proposed "comparing different MI attacks" methodology, and we have designed and implemented the MIBench benchmark with 84 evaluation scenarios for each dataset. In total, we have used our benchmark to fairly and systematically compare 15 state-of-the-art MI attack algorithms across 588 evaluation scenarios, and these evaluation scenarios cover 7 widely used datasets and 7 representative types of models. All codes and evaluations of MIBench are publicly available at https://github.com/MIBench/MIBench.github.io/blob/main/README.md.

FedDCT: A Dynamic Cross-Tier Federated Learning Scheme in Wireless Communication Networks

With the rapid proliferation of Internet of Things (IoT) devices and the growing concern for data privacy among the public, Federated Learning (FL) has gained significant attention as a privacy-preserving machine learning paradigm. FL enables the training of a global model among clients without exposing local data. However, when a federated learning system runs on wireless communication networks, limited wireless resources, heterogeneity of clients, and network transmission failures affect its performance and accuracy. In this study, we propose a novel dynamic cross-tier FL scheme, named FedDCT to increase training accuracy and performance in wireless communication networks. We utilize a tiering algorithm that dynamically divides clients into different tiers according to specific indicators and assigns specific timeout thresholds to each tier to reduce the training time required. To improve the accuracy of the model without increasing the training time, we introduce a cross-tier client selection algorithm that can effectively select the tiers and participants. Simulation experiments show that our scheme can make the model converge faster and achieve a higher accuracy in wireless communication networks.

C$^3$PS: Context-aware Conditional Cross Pseudo Supervision for Semi-supervised Medical Image Segmentation

Semi-supervised learning (SSL) methods, which can leverage a large amount of unlabeled data for improved performance, has attracted increasing attention recently. In this paper, we introduce a novel Context-aware Conditional Cross Pseudo Supervision method (referred as C$^3$PS) for semi-supervised medical image segmentation. Unlike previously published Cross Pseudo Supervision (CPS) works, this paper introduces a novel Conditional Cross Pseudo Supervision (CCPS) mechanism where the cross pseudo supervision is conditioned on a given class label. Context-awareness is further introduced in the CCPS to improve the quality of pseudo-labels for cross pseudo supervision. The proposed method has the additional advantage that in the later training stage, it can focus on the learning of hard organs. Validated on two typical yet challenging medical image segmentation tasks, our method demonstrates superior performance over the state-of-the-art methods.

Behavior Contrastive Learning for Unsupervised Skill Discovery

In reinforcement learning, unsupervised skill discovery aims to learn diverse skills without extrinsic rewards. Previous methods discover skills by maximizing the mutual information (MI) between states and skills. However, such an MI objective tends to learn simple and static skills and may hinder exploration. In this paper, we propose a novel unsupervised skill discovery method through contrastive learning among behaviors, which makes the agent produce similar behaviors for the same skill and diverse behaviors for different skills. Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective. Meanwhile, our method implicitly increases the state entropy to obtain better state coverage. We evaluate our method on challenging mazes and continuous control tasks. The results show that our method generates diverse and far-reaching skills, and also obtains competitive performance in downstream tasks compared to the state-of-the-art methods.