Related papers: Scheming in the wild: detecting real-world AI sche…
The rapid advancement of information technology has introduced a noticeable shift from traditional offline practices to more efficient and interconnected online environments. This transition, while offering convenience, has also increased…
Today's leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about…
Global biodiversity is declining at an unprecedented rate, yet little information is known about most species and how their populations are changing. Indeed, some 90% of Earth's species are estimated to be completely unknown. Machine…
This paper introduces ChatbotManip, a novel dataset for studying manipulation in Chatbots. It contains simulated generated conversations between a chatbot and a (simulated) user, where the chatbot is explicitly asked to showcase…
Online scams often unfold gradually through interaction, yet existing detection systems predominantly rely on snapshot-based signals and interruptive warnings, revealing two research gaps in the lack of signals that represent scam risk…
Artificial intelligence (AI) is often presented as a key tool for addressing societal challenges, such as climate change. At the same time, AI's environmental footprint is expanding increasingly. This report describes the systemic…
The serious privacy and security problems related to online social networks (OSNs) are what fueled two complementary studies as part of this thesis. In the first study, we developed a general algorithm for the mining of data of targeted…
Tools that can generate computer code in response to inputs written in natural language, such as ChatGPT, pose an existential threat to Computer Science education in its current form, since students can now use these tools to solve…
As AI agents surpass human capabilities, scalable oversight -- the problem of effectively supplying human feedback to potentially superhuman AI models -- becomes increasingly critical to ensure alignment. While numerous scalable oversight…
As artificial intelligence (AI) becomes increasingly embedded in the core functions of social, political, and economic life, it catalyzes structural transformations with far-reaching societal implications. This paper advances the concept of…
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…
Evaluating AI safety requires statistically rigorous methods and risk metrics for understanding how the use of AI affects aggregated risk. However, much AI safety literature focuses upon risks arising from AI models in isolation, lacking…
From just a short glance at a video, we can often tell whether a person's action is intentional or not. Can we train a model to recognize this? We introduce a dataset of in-the-wild videos of unintentional action, as well as a suite of…
Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts. Imitation learning has emerged as one of the prominent approaches to build such…
We address the challenge of learning safe and robust decision policies in presence of uncertainty in context of the real scientific problem of adaptive resource oversubscription to enhance resource efficiency while ensuring safety against…
Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…
Although general-purpose AI systems offer transformational opportunities in science and industry, they simultaneously raise critical concerns about safety, misuse, and potential loss of control. Despite these risks, methods for assessing…
This paper proposes a machine learning-based approach for detecting the exploitation of vulnerabilities in the wild by monitoring underground hacking forums. The increasing volume of posts discussing exploitation in the wild calls for an…
With the rapid diffusion of social networks in combination with mobile phones, a new social threat of sextortion has emerged, in which vulnerable young women are essentially blackmailed with their explicit shared multimedia content. The…
Investigating efficiently the data collected from a system's activity can help to detect malicious attempts and better understand the context behind past incident occurrences. Nowadays, several solutions can be used to monitor system…