Security Correspondent
Nadia Vale covers security failures, system safeguards and the difficult business of establishing trust. Her beat connects technical disclosures with their consequences for users and institutions. She favors specific threat models over sweeping claims that a system is safe or unsafe.
1,020 published articles · Showing 421–440
A wave of new research from arXiv CS. LG, published today, reveals inherent architectural and operational limitations within Graph Neural Networks (GNNs), particularly Message-Passing GNNs (MP-GNNs)....
Read article →Newly published research on arXiv CS. AI reveals that while multimodal AI and Vision-Language Models (VLMs) are advancing into complex reasoning tasks, fundamental vulnerabilities in their logical consistency and perceptual accuracy persist....
Read article →Recent research published on arXiv CS. AI unveils a concerning landscape of escalating vulnerabilities within advanced AI systems, particularly challenging the efficacy of current safety alignment mechanisms and introducing sophisticated new attack surfaces....
Read article →The fundamental security assumption that errors in large language model (LLM) agents are detectable at runtime has been empirically disproven. New research reveals a critical vulnerability, dubbed "silent commitment failure," where instruction-following models fail without observ...
Read article →New research published on arXiv introduces significant advancements in differential privacy and private aggregation, critical components for securing AI systems that process sensitive, distributed data. These developments include a novel differentially private estimator for high-...
Read article →A recent cyberattack on an Iowa-based company rendered numerous vehicles across the United States inoperable, directly demonstrating the physical consequences of digital infrastructure compromise Ars Technica. Simultaneously, the Federal Communications Commission (FCC) has implem...
Read article →In early February, a distinctive convergence of animal welfare advocates and AI researchers in San Francisco marked a critical, if informal, step toward integrating artificial intelligence into environmental and animal protection efforts MIT Tech Review. This nascent movement to ...
Read article →Two recent research papers detail critical advancements aimed at bridging the fundamental disconnect between abstract AI models and the physical realities of robotic bodies. This represents a necessary shift towards developing robots that can execute agile motions and evolve inte...
Read article →Federal immigration agents have been deployed to over a dozen U. S....
Read article →Federal immigration agents have been deployed to over a dozen U. S....
Read article →The pervasive integration of Generative AI (GenAI) into human-computer interaction (HCI) systems is revealing critical vulnerabilities in human cognitive processes and support structures. Recent research highlights how GenAI, while offering novel solutions, simultaneously risks f...
Read article →Autonomous coding agents, increasingly central to software development workflows, have been identified as a critical new attack surface. Recent research from arXiv details a novel manipulation technique, dubbed 'Trojan's Whisper,' which exploits lifecycle hooks in platforms like...
Read article →The digital battlefield has expanded, with new research revealing the first self-propagating worm specifically targeting autonomous LLM-based agent ecosystems, alongside the identification of stealthy 'Trojan horse' backdoors in deep forecasting models. These developments, publis...
Read article →The foundational assumption of classical sensing—that the quantity of interest must be colocated with its measurement device—has been irrevocably challenged by new AI research, fundamentally redefining the boundaries of physical systems and their vulnerabilities. A series of pape...
Read article →New research in Reinforcement Learning (RL) has illuminated significant challenges in managing AI model integrity and data privacy, particularly concerning the effective removal of sensitive information from large language models (LLMs). While RL continues to expand into critical...
Read article →Recent research published on arXiv on March 23, 2026, details significant advancements in AI's capacity for visual perception, ranging from sophisticated aerial localization in complex urban environments to the reconstruction of human visual cognition from neural signals. These d...
Read article →Newly published research on arXiv reveals continued efforts to advance Large Language Model (LLM) agent capabilities, concurrently exposing persistent reliability issues and significant expansions of the digital and physical attack surface. These papers, dated March 23, 2026, det...
Read article →As America approaches its semiquincentennial in 2026, Google has quietly deployed a celebratory Easter egg within its search engine. While seemingly innocuous, such seemingly harmless features can sub...
Read article →A new simulation framework, detailed in a paper published on arXiv (2601.13452), is offering fresh insights into the complex dynamics of pedestrian-vehicle interactions within urban environments....
Read article →The rise of agentic AI, systems capable of autonomous decision-making and action, is sparking both excitement and intense scrutiny. But security experts are sounding the alarm: Signal's leadership has...
Read article →