WebP, as an image format increasingly adopted across the internet, is becoming an important cover for steganography, yet its steganographic capacity remains largely unexplored. The distinctive structure of lossy WebP compression, particularly its predictive coding and uniform quantization, poses significant challenges to conventional embedding cost modeling. These include nonlinear relationship between Discrete Cosine Transform (DCT) coefficients and reconstruction pixels, quantization uniformity obscuring frequency sensitivity, and distortion propagation across blocks. To address these challenges, we propose WebP-Adaptive Residual-reconstruction-united and Predictive-aware steganography (WARP), a novel embedding framework specifically designed for WebP images. WARP introduces a unified cost modeling paradigm that integrates reconstruction-domain texture complexity, residual-frequency quantization behavior, and predictive coding order. Specifically, it precisely identifies secure embedding regions by calculating reconstruction-domain texture-adaptive costs and then refining them with residual-domain frequency sensitivity. Furthermore, to mitigate inter-block distortion propagation inherent in predictive coding, WARP incorporates a novel predictive-order-aware cost decay mechanism that adjusts embedding costs based on block coordinates. To the best of our knowledge, this work represents the first comprehensive study on secure adaptive WebP steganography. Extensive experiments demonstrate that WARP achieves superior security performance against state-of-the-art steganalysis while maintaining high visual quality.

Abstract Artificial intelligence (AI) is revolutionizing both industries and reshaping the global economy. However, the rapid advancement of AI technologies brings significant security and privacy challenges. Recent incidents highlight vulnerabilities in AI systems, such as data leakage and malicious code injection, leading to severe financial losses and privacy breaches. Although existing studies have discussed specific security threats, they often lack detailed granularity and cover a limited scope. In this survey, we fill this gap by systematically categorizing and analyzing the threats and countermeasures in AI systems, which span both the training and inference stages, encompass centralized and distributed settings, and address both conventional and foundation AI models. By reviewing existing literature, we aim to provide AI researchers and practitioners with a thorough understanding of system vulnerabilities and current countermeasures. We hope to inspire further research into robust solutions, ultimately contributing to the development of resilient AI technologies.

Face authentication has become prevalent in our daily lives. However, mainstream vision-based face authentication systems suffer from some limitations, including poor performance in dark environments, vulnerability to spoofing attacks, and privacy concerns. This paper proposes EchoLive, an acoustic-based 3D dynamic face authentication system that leverages acoustic sensors on mobile devices to sense the 3D dynamic facial cues for authentication. It utilizes the speaker to emit ultrasonic acoustic signals and the microphone to receive the echo signals from the user's face. From the echo signals, we can extract users' unique 3D facial geometry and dynamic facial information (i.e., head movements) and then perform reliable and secure 3D dynamic authentication. Utilizing acoustic sensing technology, EchoLive exhibits robustness under various environmental lighting and noise conditions, providing strong security guarantees and alleviating user concerns about the privacy of visual facial data. Extensive experiments show that EchoLive can realize reliable 3D dynamic face authentication and defend against mainstream spoofing attacks well.

The main goal of Encryption as a Service (EaaS) is to deliver cryptography services to limited-resource devices. However, due to the massive number of devices connecting EaaS platforms, they face challenging issues, such as high service delays and uncovered requests. The existing EaaS architectures lack in adequately taking advantage of both cloud and fog layers, by which the performance can be improved. Therefore, this article proposes a novel EaaS architecture called full-cloud-fog that focuses on increasing the EaaS throughput by locating the frequently accessed components on the fog layer and resolving resource allocations utilizing the cloud nodes. We have analyzed the security aspects of the proposed architecture and then implemented it in a real testbed. The evaluation results show that the proposed full-cloud-fog architecture improves the EaaS throughput by 81%.

The widespread adoption of Internet of Things (IoT) technology has introduced new cybersecurity challenges. Encryption services are being offloaded to cloud and fog platforms to mitigate these risks. Encryption as a Service (EaaS) emerges as a remedy, offering cryptographic solutions tailored to the resource constraints of IoT devices. This study thoroughly examines existing EaaS platforms, categorizing them based on encryption algorithms and service offerings. Additionally, we outline various EaaS architecture types depending on the placement of key components. Practical implementations of these platforms are explored through different testbeds. A key focus lies in dissecting the challenges that EaaS faces, particularly in the context of IoT, while suggesting potential remedies. This work stands out as an all-encompassing exploration, bridging the gap left by previous surveys.

Recent advancements in adversarial attack research have seen a transition from white-box to black-box and even no-box threat models, greatly enhancing the practicality of these attacks. However, existing no-box attacks focus on instance-specific perturbations, leaving more powerful universal adversarial perturbations (UAPs) unexplored. This study addresses a crucial question: can UAPs be generated under a no-box threat model? Our findings provide an affirmative answer with a texture-based method. Artificially crafted textures can act as UAPs, termed Texture-Adv. With a modest density and a fixed budget for perturbations, it can achieve an attack success rate of 80% under the constraint of$l_{\infty }$= 10/255. In addition, Texture-Adv can also take effect under traditional black-box threat models. Building upon a phenomenon associated with dominant labels, we utilize Texture-Adv to develop a highly efficient decision-based attack strategy, named Adv-Pool. This approach creates and traverses a set of Texture-Adv instances with diverse classification distributions, significantly reducing the average query budget to less than 1.3, which is near the 1-query lower bound for decision-based attacks. Moreover, we empirically demonstrate that Texture-Adv, when used as a starting point, can enhance the success rates of existing transfer attacks and the efficiency of decision-based attacks. The discovery suggests its potential as an effective starting point for various adversarial attacks while preserving the original constraints of their threat models.

The International Classification of Diseases (ICD) is a standard for categorizing physical conditions, which has been widely used for analyzing clinical data and monitoring health issues. Manual ICD coding takes a long time and is vulnerable to errors, so people pay more and more attention to the application of deep neural networks in ICD automatic coding. However, there is still no comprehensive review of these studies and prospects for further research. This paper is not limited to the study of deep neural networks, but gives a formal definition of ICD coding problems, and then systematically reviews the existing literature on how to design deep neural networks to address the four major challenges of ICD coding tasks. This paper also summarizes the public data sets and future research directions, to provide a guidance for the research of ICD coding in medical field.

A fundamental issue of 6G networks with aerial access networks (AAN) as a core component is that user devices will send high‐volume traffic via AAN to backend servers. As such, it is critical to load balance such traffic such that it will not cause network congestion or disruption and affect users’ experience in 6G networks. Motivated by the success of software‐defined networking‐based load balancing, this paper proposes a novel system called Tigris, to load balance high‐volume AAN traffic in 6G networks. Different from existing load balancing solutions in traditional networks, Tigris tackles the fundamental disruption-resistant challenge in 6G networks for avoiding disruption of continuing flows and the control-path update challenge for limiting the throughput of updating load balancing instructions. Tigris achieves disruption‐free and low‐control‐path‐cost load balancing for AAN traffic by developing an online algorithm to compute disruption‐resistant, per‐flow load balancing policies and a novel bottom‐up algorithm to compile the per‐flow policies into a highly compact rule set, which remains disruption‐resistant and has a low control‐path cost. We use extensive evaluation to demonstrate the efficiency and efficacy of Tigris to achieve zero disruption of continuing AAN flows and an extremely low control‐path update overhead, while existing load balancing techniques in traditional networks such as ECMP cause high load variance and disrupt almost 100% continuing AAN flows.