Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image, resulting in excessive noise that overfit the source model. Concentrating perturbation to dominant image regions that are model-agnostic is crucial to improving adversarial efficacy. However, limiting perturbation to local regions in the spatial domain proves inadequate in augmenting transferability. To this end, we propose a transferable adversarial attack with fine-grained perturbation optimization in the frequency domain, creating centralized perturbation. We devise a systematic pipeline to dynamically constrain perturbation optimization to dominant frequency coefficients. The constraint is optimized in parallel at each iteration, ensuring the directional alignment of perturbation optimization with model prediction. Our approach allows us to centralize perturbation towards sample-specific important frequency features, which are shared by DNNs, effectively mitigating source model overfitting. Experiments demonstrate that by dynamically centralizing perturbation on dominating frequency coefficients, crafted adversarial examples exhibit stronger transferability, and allowing them to bypass various defenses.
相關內容
Spear-phishing attacks present a significant security challenge, with large language models (LLMs) escalating the threat by generating convincing emails and facilitating target reconnaissance. To address this, we propose a detection approach based on a novel document vectorization method that utilizes an ensemble of LLMs to create representation vectors. By prompting LLMs to reason and respond to human-crafted questions, we quantify the presence of common persuasion principles in the email's content, producing prompted contextual document vectors for a downstream supervised machine learning model. We evaluate our method using a unique dataset generated by a proprietary system that automates target reconnaissance and spear-phishing email creation. Our method achieves a 91% F1 score in identifying LLM-generated spear-phishing emails, with the training set comprising only traditional phishing and benign emails. Key contributions include an innovative document vectorization method utilizing LLM reasoning, a publicly available dataset of high-quality spear-phishing emails, and the demonstrated effectiveness of our method in detecting such emails. This methodology can be utilized for various document classification tasks, particularly in adversarial problem domains.
Deep neural networks have achieved remarkable breakthroughs by leveraging multiple layers of data processing to extract hidden representations, albeit at the cost of large electronic computing power. To enhance energy efficiency and speed, the optical implementation of neural networks aims to harness the advantages of optical bandwidth and the energy efficiency of optical interconnections. In the absence of low-power optical nonlinearities, the challenge in the implementation of multilayer optical networks lies in realizing multiple optical layers without resorting to electronic components. In this study, we present a novel framework that uses multiple scattering that is capable of synthesizing programmable linear and nonlinear transformations concurrently at low optical power by leveraging the nonlinear relationship between the scattering potential, represented by data, and the scattered field. Theoretical and experimental investigations show that repeating the data by multiple scattering enables non-linear optical computing at low power continuous wave light. Moreover, we empirically found that scaling of this optical framework follows the power law as in state-of-the-art deep digital networks.
One-stream Transformer trackers have shown outstanding performance in challenging benchmark datasets over the last three years, as they enable interaction between the target template and search region tokens to extract target-oriented features with mutual guidance. Previous approaches allow free bidirectional information flow between template and search tokens without investigating their influence on the tracker's discriminative capability. In this study, we conducted a detailed study on the information flow of the tokens and based on the findings, we propose a novel Optimized Information Flow Tracking (OIFTrack) framework to enhance the discriminative capability of the tracker. The proposed OIFTrack blocks the interaction from all search tokens to target template tokens in early encoder layers, as the large number of non-target tokens in the search region diminishes the importance of target-specific features. In the deeper encoder layers of the proposed tracker, search tokens are partitioned into target search tokens and non-target search tokens, allowing bidirectional flow from target search tokens to template tokens to capture the appearance changes of the target. In addition, since the proposed tracker incorporates dynamic background cues, distractor objects are successfully avoided by capturing the surrounding information of the target. The OIFTrack demonstrated outstanding performance in challenging benchmarks, particularly excelling in the one-shot tracking benchmark GOT-10k, achieving an average overlap of 74.6\%. The code, models, and results of this work are available at \url{//github.com/JananiKugaa/OIFTrack}
Weakly supervised instance segmentation (WSIS) using only image-level labels is a challenging task due to the difficulty of aligning coarse annotations with the finer task. However, with the advancement of deep neural networks (DNNs), WSIS has garnered significant attention. Following a proposal-based paradigm, we encounter a redundant segmentation problem resulting from a single instance being represented by multiple proposals. For example, we feed a picture of a dog and proposals into the network and expect to output only one proposal containing a dog, but the network outputs multiple proposals. To address this problem, we propose a novel approach for WSIS that focuses on the online refinement of complete instances through the use of MaskIoU heads to predict the integrity scores of proposals and a Complete Instances Mining (CIM) strategy to explicitly model the redundant segmentation problem and generate refined pseudo labels. Our approach allows the network to become aware of multiple instances and complete instances, and we further improve its robustness through the incorporation of an Anti-noise strategy. Empirical evaluations on the PASCAL VOC 2012 and MS COCO datasets demonstrate that our method achieves state-of-the-art performance with a notable margin. Our implementation will be made available at //github.com/ZechengLi19/CIM.
We consider a base station (BS) that receives version update packets from multiple exogenous streams and broadcasts them to corresponding users over a fading broadcast channel using a non-orthogonal multiple access (NOMA) scheme. Sequentially indexed packets arrive randomly in each stream, with new packets making the previous ones obsolete. In this case, we consider the version age of information (VAoI) at a user, defined as the difference in the version index of the latest available packet at the BS and that at the user, as a metric of freshness of information. Our objective is to minimize a weighted sum of average VAoI across users subject to an average power constraint at the BS by optimally scheduling the update packets from various streams for transmission and transmitting them with sufficient powers to guarantee their successful delivery. We consider the class of channel-only stationary randomized policies (CO-SRP), which rely solely on channel power gains for transmission decisions. We solve the resulting non-convex problem optimally and show that the VAoI achieved under the optimal CO-SRP is within twice the optimal achievable VAoI. We also obtained a Constrained Markov Decision Process (CMDP)-based solution and its structural properties. Numerical simulations show a close performance between the optimal CO-SRP and CMDP-based solutions. Additionally, a time division multiple access (TDMA) scheme, which allows transmission to at most one user at a time, matches NOMA's performance under tight average power constraints. However, NOMA outperforms TDMA as the constraint is relaxed.
The social media-fuelled explosion of fake news and misinformation supported by tampered images has led to growth in the development of models and datasets for image manipulation detection. However, existing detection methods mostly treat media objects in isolation, without considering the impact of specific manipulations on viewer perception. Forensic datasets are usually analyzed based on the manipulation operations and corresponding pixel-based masks, but not on the semantics of the manipulation, i.e., type of scene, objects, and viewers' attention to scene content. The semantics of the manipulation play an important role in spreading misinformation through manipulated images. In an attempt to encourage further development of semantic-aware forensic approaches to understand visual misinformation, we propose a framework to analyze the trends of visual and semantic saliency in popular image manipulation datasets and their impact on detection.
Multimedia services over mobile networks pose several challenges, such as the efficient management of radio resources or the latency induced by network delays and buffering requirements on the multimedia players. In Long Term Evolution (LTE) networks, the definition of multimedia broadcast services over a common radio channel addresses the shortage of radio resources but introduces the problem of network error recovery. In order to address network errors on LTE multimedia broadcast services, the current standards propose the combined use of forward error correction and unicast recovery techniques at the application level. This paper shows how to efficiently synchronize the broadcasting server and the multimedia players and how to reduce service latency by limiting the multimedia player buffer length. This is accomplished by analyzing the relation between the different parameters of the LTE multimedia broadcast service, the multimedia player buffer length, and service interruptions. A case study is simulated to confirm how the quality of the multimedia service is improved by applying our proposals.
The real-world data tends to be heavily imbalanced and severely skew the data-driven deep neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task. Existing LTR methods seldom train Vision Transformers (ViTs) with Long-Tailed (LT) data, while the off-the-shelf pretrain weight of ViTs always leads to unfair comparisons. In this paper, we systematically investigate the ViTs' performance in LTR and propose LiVT to train ViTs from scratch only with LT data. With the observation that ViTs suffer more severe LTR problems, we conduct Masked Generative Pretraining (MGP) to learn generalized features. With ample and solid evidence, we show that MGP is more robust than supervised manners. In addition, Binary Cross Entropy (BCE) loss, which shows conspicuous performance with ViTs, encounters predicaments in LTR. We further propose the balanced BCE to ameliorate it with strong theoretical groundings. Specially, we derive the unbiased extension of Sigmoid and compensate extra logit margins to deploy it. Our Bal-BCE contributes to the quick convergence of ViTs in just a few epochs. Extensive experiments demonstrate that with MGP and Bal-BCE, LiVT successfully trains ViTs well without any additional data and outperforms comparable state-of-the-art methods significantly, e.g., our ViT-B achieves 81.0% Top-1 accuracy in iNaturalist 2018 without bells and whistles. Code is available at //github.com/XuZhengzhuo/LiVT.
Emotion plays an important role in detecting fake news online. When leveraging emotional signals, the existing methods focus on exploiting the emotions of news contents that conveyed by the publishers (i.e., publisher emotion). However, fake news is always fabricated to evoke high-arousal or activating emotions of people to spread like a virus, so the emotions of news comments that aroused by the crowd (i.e., social emotion) can not be ignored. Furthermore, it needs to be explored whether there exists a relationship between publisher emotion and social emotion (i.e., dual emotion), and how the dual emotion appears in fake news. In the paper, we propose Dual Emotion Features to mine dual emotion and the relationship between them for fake news detection. And we design a universal paradigm to plug it into any existing detectors as an enhancement. Experimental results on three real-world datasets indicate the effectiveness of the proposed features.
Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising. Specifically, our networks contain blocks that denoise the features using non-local means or other filters; the entire networks are trained end-to-end. When combined with adversarial training, our feature denoising networks substantially improve the state-of-the-art in adversarial robustness in both white-box and black-box attack settings. On ImageNet, under 10-iteration PGD white-box attacks where prior art has 27.9% accuracy, our method achieves 55.7%; even under extreme 2000-iteration PGD white-box attacks, our method secures 42.6% accuracy. A network based on our method was ranked first in Competition on Adversarial Attacks and Defenses (CAAD) 2018 --- it achieved 50.6% classification accuracy on a secret, ImageNet-like test dataset against 48 unknown attackers, surpassing the runner-up approach by ~10%. Code and models will be made publicly available.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191