Monash University and the Australian Federal Police (AFP) are teaming up to turn the tech tables on cybercriminals through a dose of digital poison.

تعاونت جامعة موناش مع الشرطة الفيدرالية الأسترالية لتطوير أداة جديدة تعتمد على الذكاء الاصطناعي تهدف إلى مكافحة الصور المزيفة الضارة. هذه الشراكة مهمة لأنها تسعى لمواجهة التهديد المتزايد الذي يشكله المجرمون الإلكترونيون الذين يستغلون هذه التكنولوجيا لأغراض ضارة.

La Universidad de Monash y la Policía Federal Australiana han desarrollado una nueva herramienta de IA destinada a combatir imágenes deepfake maliciosas. Esta colaboración es significativa ya que busca contrarrestar la creciente amenaza que representan los cibercriminales que explotan esta tecnología con fines dañinos.

L'Université de Monash et la Police fédérale australienne ont développé un nouvel outil d'IA visant à lutter contre les images deepfake malveillantes. Cette collaboration est importante car elle cherche à contrer la menace croissante posée par les cybercriminels qui exploitent cette technologie à des fins nuisibles.

Monash University and the Australian Federal Police have developed a new AI tool aimed at combating malicious deepfake images. This collaboration is significant as it seeks to counteract the growing threat posed by cybercriminals who exploit such technology for harmful purposes.

Poisoned pixels: New AI tool to fight malicious deepfake images

arXiv:1906.07172v5 Announce Type: replace-cross 
Abstract: Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.

Equivariant neural networks and equivarification

arXiv:2311.13745v4 Announce Type: replace-cross 
Abstract: Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the sample complexity of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.

Improved Sample Complexity Bounds for Diffusion Model Training

arXiv:2410.22995v2 Announce Type: replace-cross 
Abstract: A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids. To this end, we introduce \textbf{VisAidMath}, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound ``Reasoning Illusion''. We observe that high surface-level accuracy conceals a catastrophic failure in the models' ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We host an evaluation platform at CodaBench for testing publicly. Homepage: https://nlp2ct.github.io/VisAidMathHomepage/ Evaluation: https://www.codabench.org/competitions/7634/

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning

arXiv:2508.01249v3 Announce Type: replace-cross 
Abstract: Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces critical security risks, particularly in the presence of prompt injection attacks. In this work, we propose a novel insight that treats the agent runtime traces as structured programs with analyzable semantics. Thus, we present AgentArmor, a program analysis framework that converts agent traces into graph intermediate representation-based structured program dependency representations (e.g., CFG, DFG, and PDG) and enforces security policies via a type system. AgentArmor consists of three key components: (1) a graph constructor that reconstructs the agent's runtime traces as graph-based intermediate representations with control and data flow described within; (2) a property registry that attaches security-relevant metadata of interacted tools \& data, and (3) a type system that performs static inference and checking over the intermediate representation. By representing agent behavior as structured programs, AgentArmor enables program analysis for sensitive data flow, trust boundaries, and policy violations. We evaluate AgentArmor on the AgentDojo benchmark, the results show that AgentArmor can reduce the ASR to 3\%, with the utility drop only 1\%.

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection

arXiv:2511.14691v1 Announce Type: cross 
Abstract: Attention is the brain's ability to selectively focus on a few specific aspects while ignoring irrelevant ones. This biological principle inspired the attention mechanism in modern Transformers. Transformers now underpin large language models (LLMs) such as GPT, but at the cost of massive training and inference energy, leading to a large carbon footprint. While brain attention emerges from neural circuits, Transformer attention relies on dot-product similarity to weight elements in the input sequence. Neuromorphic computing, especially spiking neural networks (SNNs), offers a brain-inspired path to energy-efficient intelligence. Despite recent work on attention-based spiking Transformers, the core attention layer remains non-neuromorphic. Current spiking attention (i) relies on dot-product or element-wise similarity suited to floating-point operations, not event-driven spikes; (ii) keeps attention matrices that suffer from the von Neumann bottleneck, limiting in-memory computing; and (iii) still diverges from brain-like computation. To address these issues, we propose the Spiking STDP Transformer (S$^{2}$TDPT), a neuromorphic Transformer that implements self-attention through spike-timing-dependent plasticity (STDP), embedding query--key correlations in synaptic weights. STDP, a core mechanism of memory and learning in the brain and widely studied in neuromorphic devices, naturally enables in-memory computing and supports non-von Neumann hardware. On CIFAR-10 and CIFAR-100, our model achieves 94.35\% and 78.08\% accuracy with only four timesteps and 0.49 mJ on CIFAR-100, an 88.47\% energy reduction compared to a standard ANN Transformer. Grad-CAM shows that the model attends to semantically relevant regions, enhancing interpretability. Overall, S$^{2}$TDPT illustrates how biologically inspired attention can yield energy-efficient, hardware-friendly, and explainable neuromorphic models.

Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer

arXiv:2511.08955v2 Announce Type: replace-cross 
Abstract: Simulating microstructure evolution (MicroEvo) is vital for materials design but demands high numerical accuracy, efficiency, and physical fidelity. Although recent studies on deep learning (DL) offer a promising alternative to traditional solvers, the field lacks standardized benchmarks. Existing studies are flawed due to a lack of comparing specialized MicroEvo DL models with state-of-the-art spatio-temporal architectures, an overemphasis on numerical accuracy over physical fidelity, and a failure to analyze error propagation over time. To address these gaps, we introduce MicroEvoEval, the first comprehensive benchmark for image-based microstructure evolution prediction. We evaluate 14 models, encompassing both domain-specific and general-purpose architectures, across four representative MicroEvo tasks with datasets specifically structured for both short- and long-term assessment. Our multi-faceted evaluation framework goes beyond numerical accuracy and computational cost, incorporating a curated set of structure-preserving metrics to assess physical fidelity. Our extensive evaluations yield several key insights. Notably, we find that modern architectures (e.g., VMamba), not only achieve superior long-term stability and physical fidelity but also operate with an order-of-magnitude greater computational efficiency. The results highlight the necessity of holistic evaluation and identify these modern architectures as a highly promising direction for developing efficient and reliable surrogate models in data-driven materials science.

MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction

Turning materials like wood chips, crop residues and municipal solid waste into fuels and chemicals is important for our country's energy independence.

طور الباحثون نماذج حاسوبية متقدمة تهدف إلى تحسين التنبؤات لعمليات طحن الكتلة الحيوية. تركز هذه الابتكارات على تحويل مواد مثل رقائق الخشب، بقايا المحاصيل، والنفايات الصلبة البلدية إلى وقود ومواد كيميائية قيمة، وهو أمر مهم لتعزيز استقلالية الطاقة في البلاد. من المتوقع أن تعمل النماذج على تحسين كفاءة معالجة الكتلة الحيوية، مما يساهم في حلول الطاقة المستدامة.

Investigadores han desarrollado modelos informáticos avanzados destinados a mejorar las predicciones para los procesos de molienda de biomasa. Esta innovación se centra en convertir materiales como astillas de madera, residuos de cultivos y residuos sólidos municipales en combustibles y productos químicos valiosos, lo que es crucial para mejorar la independencia energética del país. Se espera que los modelos optimicen la eficiencia del procesamiento de biomasa, contribuyendo así a soluciones energéticas sostenibles.

Des chercheurs ont développé des modèles informatiques avancés visant à améliorer les prévisions pour les processus de broyage de la biomasse. Cette innovation se concentre sur la conversion de matériaux tels que les copeaux de bois, les résidus de culture et les déchets solides municipaux en combustibles et produits chimiques précieux, ce qui est crucial pour renforcer l'indépendance énergétique du pays. Les modèles devraient optimiser l'efficacité du traitement de la biomasse, contribuant ainsi à des solutions énergétiques durables.

Researchers have developed advanced computer models aimed at improving predictions for biomass milling processes. This innovation focuses on converting materials such as wood chips, crop residues, and municipal solid waste into valuable fuels and chemicals, which is crucial for enhancing energy independence in the country. The models are expected to optimize the efficiency of biomass processing, thereby contributing to sustainable energy solutions.

Researchers develop computer models for better biomass milling predictions

Robots that can sense and respond to the world like humans may soon be a reality as scientists have created an artificial neuron capable of mimicking different parts of the brain.

طور العلماء نيوترونًا صناعيًا يمكنه تقليد أجزاء مختلفة من الدماغ، مما يمثل خطوة كبيرة نحو إنشاء روبوتات يمكنها الإحساس والاستجابة للعالم مثل البشر. قد تفتح هذه الابتكارات الطريق نحو روبوتات أكثر تطورًا، مما يعزز التفاعل بين الآلات وبيئتها.

Científicos han desarrollado un neurón artificial que puede imitar diferentes partes del cerebro, marcando un avance significativo hacia la creación de robots que pueden sentir y responder a su entorno como los humanos. Esta innovación podría allanar el camino para una robótica más sofisticada, mejorando la interacción entre las máquinas y su entorno.

Des scientifiques ont développé un neurone artificiel capable de mimer différentes parties du cerveau, marquant une avancée significative vers la création de robots capables de percevoir et de réagir à leur environnement comme des humains. Cette innovation pourrait ouvrir la voie à des robots plus sophistiqués, améliorant l'interaction entre les machines et leur environnement.

Scientists have developed an artificial neuron that can mimic various parts of the brain, marking a significant advancement toward creating robots that can sense and respond to their environment like humans. This innovation could pave the way for more sophisticated human-like robotics, enhancing the interaction between machines and their surroundings.

Artificial neuron can mimic different parts of the brain—a major step toward human-like robotics

You've just finished a strenuous hike to the top of a mountain. You're exhausted but elated. The view of the city below is gorgeous, and you want to capture the moment on camera. But it's already quite dark, and you're not sure you'll get a good shot. Fortunately, your phone has an AI-powered night mode that can take stunning photos even after sunset.

يتناول المقال دور البيانات الاصطناعية في تدريب أنظمة الذكاء الاصطناعي (AI) لمواجهة التحديات الواقعية. يبرز سيناريو حيث يستخدم شخص ما، بعد رحلة شاقة، وضع الليل المدعوم بالذكاء الاصطناعي في هاتفه لالتقاط صور مذهلة في ظروف الإضاءة المنخفضة. وهذا يعكس التطبيق العملي لتكنولوجيا الذكاء الاصطناعي في تحسين التجارب اليومية، خاصة في التصوير الفوتوغرافي، من خلال استخدام البيانات الاصطناعية لتحسين الأداء في البيئات الصعبة.

El artículo aborda el papel de los datos sintéticos en la formación de sistemas de inteligencia artificial (IA) para enfrentar desafíos del mundo real. Destaca un escenario en el que una persona, tras una agotadora caminata, utiliza el modo nocturno impulsado por IA de su teléfono para capturar impresionantes fotos en condiciones de poca luz. Esto muestra la aplicación práctica de la tecnología de IA para mejorar las experiencias cotidianas, especialmente en la fotografía, al utilizar datos sintéticos para mejorar el rendimiento en entornos desafiantes.

L'article traite du rôle des données synthétiques dans la formation des systèmes d'intelligence artificielle (IA) pour relever des défis du monde réel. Il met en avant un scénario où une personne, après une randonnée fatigante, utilise le mode nuit alimenté par l'IA de son téléphone pour capturer des photos époustouflantes dans des conditions de faible luminosité. Cela illustre l'application pratique de la technologie IA pour améliorer les expériences quotidiennes, notamment en photographie, en utilisant des données synthétiques pour améliorer les performances dans des environnements difficile…

The article discusses the role of synthetic data in training artificial intelligence (AI) systems to address real-world challenges. It highlights a scenario where an individual, after a tiring hike, uses an AI-powered night mode on their phone to capture stunning photos in low light conditions. This showcases the practical application of AI technology in enhancing everyday experiences, particularly in photography, by utilizing synthetic data to improve performance in challenging environments.

Poisoned pixels: New AI tool to fight malicious deepfake images

Was this article worth reading? Share it