Related papers: Structural Representations for Cross-Attack Genera…
We introduce an increasing-complexity, open-ended, and human-agnostic metric to evaluate foundational and frontier AI models in the context of Artificial General Intelligence (AGI) and Artificial Super Intelligence (ASI) claims. Unlike…
Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and…
Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel jailbreaks represents a critical challenge in AI safety. Adversarial training -- designed to make…
Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…
The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve…
With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…
Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…
AI-synthesized voice technology has the potential to create realistic human voices for beneficial applications, but it can also be misused for malicious purposes. While existing AI-synthesized voice detection models excel in intra-domain…
This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the…
Recent AI media detectors report near-perfect performance under clean laboratory evaluation, yet their robustness under realistic deployment conditions remains underexplored. In practice, AI-generated images are resized, compressed,…
Agentic AI systems are increasingly deployed not in isolation, but inside social environments populated by other agents and humans, such as in social media platforms, multi-agent LLM pipelines or autonomous robotics fleets. In these…
Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes…
Adversarial attacks have become a major threat for machine learning applications. There is a growing interest in studying these attacks in the audio domain, e.g, speech and speaker recognition; and find defenses against them. In this work,…
Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…
The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual…
Understanding AI systems' inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computational mechanisms and representations learned by neural networks…
Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet its impact on the model's cognition is often overlooked. We…
The rapid development of the AI agent communication protocols, including the Model Context Protocol (MCP), Agent2Agent (A2A), Agora, and Agent Network Protocol (ANP), is reshaping how AI agents communicate with tools, services, and each…
Jailbreaking attacks on large language models pose a significant threat to AI safety by enabling the generation of harmful or restricted content. While prior work has explored both handcrafted and automated jailbreak strategies, the…