Related papers: Poster: ClawdGo: Endogenous Security Awareness Tra…

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an…

The increase in available computing power and the Deep Learning revolution have allowed the exploration of new topics and frontiers in Artificial Intelligence research. A new field called Embodied Artificial Intelligence, which places at…

Multi-agent control problems constitute an interesting area of application for deep reinforcement learning models with continuous action spaces. Such real-world applications, however, typically come with critical safety constraints that…

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…

As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…

This paper presents DeepStage, a deep reinforcement learning (DRL) framework for adaptive and stage-aware defense against Advanced Persistent Threats (APTs). The enterprise environment is formulated as a partially observable Markov decision…

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill…

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack…

We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security…

Existing defence mechanisms have demonstrated significant effectiveness in mitigating rule-based Denial-of-Service (DoS) attacks, leveraging predefined signatures and static heuristics to identify and block malicious traffic. However, the…

Adversarial Training (AT) impacts different architectures in distinct ways: vision models gain robustness but face reduced generalization, encoder-based models exhibit limited robustness improvements with minimal generalization loss, and…

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…