Adversarial prompt attacks can significantly alter the reliability of Retrieval-Augmented Generation (RAG) systems by re-ranking them to produce incorrect outputs. In this paper, we present a novel method that applies Differential Evolution (DE) to optimize adversarial prompt suffixes for RAG-based question answering. Our approach is gradient-free, treating the RAG pipeline as a black box and evolving a population of candidate suffixes to maximize the retrieval rank of a targeted incorrect document to be closer to real world scenarios. We conducted experiments on the BEIR QA datasets to evaluate attack success at certain retrieval rank thresholds under multiple retrieving applications. Our results demonstrate that DE-based prompt optimization attains competitive (and in some cases higher) success rates compared to GGPP to dense retrievers and PRADA to sparse retrievers, while using only a small number of tokens (<=5 tokens) in the adversarial suffix. Furthermore, we introduce a readability-aware suffix construction strategy, validated by a statistically significant reduction in MLM negative log-likelihood with Welch's t-test. Through evaluations with a BERT-based adversarial suffix detector, we show that DE-generated suffixes evade detection, yielding near-chance detection accuracy.

Tokenized U.S. Treasuries have emerged as a prominent subclass of real-world assets (RWAs), offering cryptographically enforced, yield-bearing instruments collateralized by sovereign debt and deployed across multiple blockchain networks. While the market has expanded rapidly, empirical analyses of transaction-level behaviour remain limited. This paper conducts a quantitative, function-level dissection of U.S. Treasury-backed RWA tokens including BUIDL, BENJI, and USDY, across multi-chain: mostly Ethereum and Layer-2s. We analyze decoded contract calls to isolate core functional primitives such as issuance, redemption, transfer, and bridge activity, revealing segmentation in behaviour between institutional actors and retail users. To model address-level economic roles, we introduce a curvature-aware representation learning framework using Poincaré embeddings and liquidity-based graph features. Our method outperforms baseline models on our RWA Treasury dataset in role inference and generalizes to downstream tasks such as anomaly detection and wallet classification in broader blockchain transaction networks. These findings provide a structured understanding of functional heterogeneity and participant roles in tokenized Treasury in a transaction-level perspective, contributing new empirical evidence to the study of on-chain financialization.

Multi-face deepfake videos are becoming increasingly prevalent, often appearing in natural social settings that challenge existing detection methods. Most current approaches excel at single-face detection but struggle in multi-face scenarios, due to a lack of awareness of crucial contextual cues. In this work, we develop a novel approach that leverages human cognition to analyze and defend against multi-face deepfake videos. Through a series of human studies, we systematically examine how people detect deepfake faces in social settings. Our quantitative analysis reveals four key cues humans rely on: scene-motion coherence, inter-face appearance compatibility, interpersonal gaze alignment, and face-body consistency. Guided by these insights, we introduce \textsf{HICOM}, a novel framework designed to detect every fake face in multi-face scenarios. Extensive experiments on benchmark datasets show that \textsf{HICOM} improves average accuracy by 3.3\% in in-dataset detection and 2.8\% under real-world perturbations. Moreover, it outperforms existing methods by 5.8\% on unseen datasets, demonstrating the generalization of human-inspired cues. \textsf{HICOM} further enhances interpretability by incorporating an LLM to provide human-readable explanations, making detection results more transparent and convincing. Our work sheds light on involving human factors to enhance defense against deepfakes.

Hyperspectral imaging (HSI) captures hundreds of narrow, contiguous wavelength bands, making it a powerful tool in biology, agriculture, and environmental monitoring. However, interpreting Vision Transformers (ViTs) in this setting remains largely unexplored due to two key challenges: (1) existing saliency methods struggle to capture meaningful spectral cues, often collapsing attention onto the class token, and (2) full-spectrum ViTs are computationally prohibitive for interpretability, given the high-dimensional nature of HSI data. We present FOCUS, the first framework that enables reliable and efficient spatial-spectral interpretability for frozen ViTs. FOCUS introduces two core components: class-specific spectral prompts that guide attention toward semantically meaningful wavelength groups, and a learnable [SINK] token trained with an attraction loss to absorb noisy or redundant attention. Together, these designs make it possible to generate stable and interpretable 3D saliency maps and spectral importance curves in a single forward pass, without any gradient backpropagation or backbone modification. FOCUS improves band-level IoU by 15 percent, reduces attention collapse by over 40 percent, and produces saliency results that align closely with expert annotations. With less than 1 percent parameter overhead, our method makes high-resolution ViT interpretability practical for real-world hyperspectral applications, bridging a long-standing gap between black-box modeling and trustworthy HSI decision-making.

Stony Brook University Figure 1: The XplainAct interface, illustrated here using the opioid dataset. Causality helps people reason about and understand complex systems, particularly through what-if analyses that explore how interventions might alter outcomes. Although existing methods embrace causal reasoning using interventions and counterfactual analysis, they primarily focus on effects at the population level. These approaches often fall short in systems characterized by significant heterogeneity, where the impact of an intervention can vary widely across subgroups. To address this challenge, we present XplainAct, a visual analytics framework that supports simulating, explaining, and reasoning interventions at the individual level within subpopulations. We demonstrate the effectiveness of XplainAct through two case studies: investigating opioid-related deaths in epidemiology and analyzing voting inclinations in the presidential election. The advances in machine learning and artificial intelligence in recent years have created a growing need for tools that can effectively support the understanding and modification of complex systems. Traditional analytical methods, which rely on correlation, merely observe how variables tend to change together.

As large language models (LLMs) become increasingly integrated into real-world applications, scalable and rigorous safety evaluation is essential. This paper introduces Aymara AI, a programmatic platform for generating and administering customized, policy-grounded safety evaluations. Aymara AI transforms natural-language safety policies into adversarial prompts and scores model responses using an AI-based rater validated against human judgments. We demonstrate its capabilities through the Aymara LLM Risk and Responsibility Matrix, which evaluates 20 commercially available LLMs across 10 real-world safety domains. Results reveal wide performance disparities, with mean safety scores ranging from 86.2% to 52.4%. While models performed well in well-established safety domains such as Misinformation (mean = 95.7%), they consistently failed in more complex or underspecified domains, notably Privacy & Impersonation (mean = 24.3%). Analyses of Variance confirmed that safety scores differed significantly across both models and domains (p < .05). These findings underscore the inconsistent and context-dependent nature of LLM safety and highlight the need for scalable, customizable tools like Aymara AI to support responsible AI development and oversight.

Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However, by sharing information such as known or suspected ongoing threats, effective communication can lead to improved decision-making in the cyber battle space. We propose a game design where defender agents learn to communicate and defend against imminent cyber threats by playing training games in the Cyber Operations Research Gym, using the Differentiable Inter Agent Learning algorithm adapted to the cyber operational environment. The tactical policies learned by these autonomous agents are akin to those of human experts during incident responses to avert cyber threats. In addition, the agents simultaneously learn minimal cost communication messages while learning their defence tactical policies.

The development of satellite-augmented low-altitude economy and terrestrial networks (SLAETNs) demands intelligent and autonomous systems that can operate reliably across heterogeneous, dynamic, and mission-critical environments. To address these challenges, this survey focuses on enabling agentic artificial intelligence (AI), that is, artificial agents capable of perceiving, reasoning, and acting, through generative AI (GAI) and large language models (LLMs). We begin by introducing the architecture and characteristics of SLAETNs, and analyzing the challenges that arise in integrating satellite, aerial, and terrestrial components. Then, we present a model-driven foundation by systematically reviewing five major categories of generative models: variational autoencoders (VAEs), generative adversarial networks (GANs), generative diffusion models (GDMs), transformer-based models (TBMs), and LLMs. Moreover, we provide a comparative analysis to highlight their generative mechanisms, capabilities, and deployment trade-offs within SLAETNs. Building on this foundation, we examine how these models empower agentic functions across three domains: communication enhancement, security and privacy protection, and intelligent satellite tasks. Finally, we outline key future directions for building scalable, adaptive, and trustworthy generative agents in SLAETNs. This survey aims to provide a unified understanding and actionable reference for advancing agentic AI in next-generation integrated networks.

One challenge in technical interviews is the think-aloud process, where candidates verbalize their thought processes while solving coding tasks. Despite its importance, opportunities for structured practice remain limited. Conversational AI offers potential assistance, but limited research explores user perceptions of its role in think-aloud practice. To address this gap, we conducted a study with 17 participants using an LLM-based technical interview practice tool. Participants valued AI's role in simulation, feedback, and learning from generated examples. Key design recommendations include promoting social presence in conversational AI for technical interview simulation, providing feedback beyond verbal content analysis, and enabling crowdsourced think-aloud examples through human-AI collaboration. Beyond feature design, we examined broader considerations, including intersectional challenges and potential strategies to address them, how AI-driven interview preparation could promote equitable learning in computing careers, and the need to rethink AI's role in interview practice by suggesting a research direction that integrates human-AI collaboration.

Fu are with the School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA. Abstract --The escalating threat of cyberattacks on real-time critical infrastructures poses significant risks to public safety, necessitating detection methods that can effectively capture complex system interdependencies and adapt to evolving attack patterns. Traditional real-time anomaly detection techniques often produce excessive false positives due to their statistical sensitivity to high data variability and class imbalance. T o address these limitations, recent research has explored modeling causal relationships among system components. However, prior work predominantly focuses on offline causal graph-based approaches that require static historical data and fail to generalize to real-time settings. These methods are fundamentally constrained by: (1) their inability to adapt to dynamic shifts in data distribution without retraining, and (2) the risk of catastrophic forgetting when lacking timely supervision in live systems. T o overcome these challenges, we propose INCADET, a novel framework for incremental causal graph learning tailored to real-time cyberat-tack detection. The framework comprises three modules: 1) Early Symptom Detection: Detects transitions in system status using divergence in edge-weight distributions across sequential causal graphs. Extensive experiments on real-world critical infrastructure datasets demonstrate that INCADET achieves superior accuracy, robustness, and adaptability compared to both static causal and deep temporal baselines in evolving attack scenarios. In real-world critical public infrastructures, adversarial cy-berattacks emerge incrementally, evolving from subtle data perturbations to complex intrusions that trigger delayed, cascading disruptions across interconnected nodes, complicating detection and mitigation.