Related papers: Behavior Associations in Lone-Actor Terrorists
Violence is commonly linked with large urban areas, and as a social phenomenon, it is presumed to scale super-linearly with population size. This study explores the hypothesis that smaller, isolated cities in Africa may experience a…
Autonomous agents can produce harmful behavioral patterns from individually valid requests -- a threat class per-request policy evaluation cannot address, because stateless engines evaluate each request in isolation. We present ACP, a…
Our study contributes to the debate on the evolution of cooperation in the single-shot Prisoner's Dilemma (PD) played on networks. We construct a model in which individuals are connected with positive and negative ties. Some agents play…
In recent years, Deep Neural Network models have been developed in different fields, where they have brought many advances. However, they have also started to be used in tasks where risk is critical. A misdiagnosis of these models can lead…
Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…
In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently…
The video-based action recognition task has been extensively studied in recent years. In this paper, we study the structural vulnerability of deep learning-based action recognition models against the adversarial attack using the one frame…
We report a remarkable universality in the patterns of violence arising in three high-profile ongoing wars, and in global terrorism. Our results suggest that these quite different conflict arenas currently feature a common type of enemy,…
Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…
In many settings, machine learning models may be used to inform decisions that impact individuals or entities who interact with the model. Such entities, or agents, may game model decisions by manipulating their inputs to the model to…
In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs. Instead, they…
Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn prompts, whereas real harassment often…
To build secure software, developers often work together during software development and maintenance to find, fix, and prevent security vulnerabilities. Examining the nature of developer interactions during their security activities…
The human action classification task is a widely researched topic and is still an open problem. Many state-of-the-arts approaches involve the usage of bag-of-video-words with spatio-temporal local features to construct characterizations for…
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…
Hate speech, offensive language, sexism, racism and other types of abusive behavior have become a common phenomenon in many online social media platforms. In recent years, such diverse abusive behaviors have been manifesting with increased…
Visual-based human action recognition can be found in various application fields, e.g., surveillance systems, sports analytics, medical assistive technologies, or human-robot interaction frameworks, and it concerns the identification and…
The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…
As computation spreads from computers to networks of computers, and migrates into cyberspace, it ceases to be globally programmable, but it remains programmable indirectly: network computations cannot be controlled, but they can be steered…
Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI. For example, while models are often studied…