Related papers: Structural Representations for Cross-Attack Genera…
We introduce CRAFT, a multi-agent benchmark for evaluating pragmatic communication in large language models under strict partial information. In this setting, multiple agents with complementary but incomplete views must coordinate through…
Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it…
Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…
Can machines truly think, reason and act in domains like humans? This enduring question continues to shape the pursuit of Artificial General Intelligence (AGI). Despite the growing capabilities of models such as GPT-4.5, DeepSeek, Claude…
Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical in order to ensure the safety and robustness of critical AI…
Modern security environments generate fragmented signals across cloud resources, identities, configurations, and third-party security tools. Although AI-native security assistants improve access to this data, they remain largely reactive:…
Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…
As training artificial intelligence (AI) models is a lengthy and hence costly process, leakage of such a model's internal parameters is highly undesirable. In the case of AI accelerators, side-channel information leakage opens up the threat…
Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…
In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not…
AI governance programmes increasingly rely on natural language prompts to constrain and direct AI agent behaviour. These prompts function as executable specifications: they define the agent's mandate, scope, and quality criteria. Despite…
Semantic communication (SemCom) redefines wireless communication from reproducing symbols to transmitting task-relevant semantics. However, this AI-native architecture also introduces new vulnerabilities, as semantic failures may arise from…
Evaluating generative AI (GenAI) systems is challenging because many targets of evaluation are broad, contested concepts, such as "reasoning," "fairness," or "creativity." When these concepts are left underspecified, it becomes unclear what…
Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…
Frontier AI Safety Policies concentrate on prevention: capability evaluations, deployment gates, and usage constraints, while neglecting the capacity to coordinate responses when prevention fails. We argue this coordination gap is…
Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…
The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…
Artificial intelligence governance exhibits a striking paradox: while major jurisdictions converge rhetorically around concepts such as safety, risk, and accountability, their regulatory frameworks remain fundamentally divergent and…
The critical need for transparent and trustworthy machine learning in cybersecurity operations drives the development of this integrated Explainable AI (XAI) framework. Our methodology addresses three fundamental challenges in deploying AI…
Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic topological hierarchies, creating ``semantic fragmentation'' that degrades downstream…