Related papers: CTRL-ALT-DECEIT: Sabotage Evaluations for Automate…
Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new challenges for verifying visual evidence. A concrete emerging risk is AI-generated refund…
Recent capability increases in large language models (LLMs) open up applications in which groups of communicating generative AI agents solve joint tasks. This poses privacy and security challenges concerning the unauthorised sharing of…
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…
As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…
Recent research has demonstrated the effectiveness of Artificial Intelligence (AI), and more specifically, Large Language Models (LLMs), in supporting network configuration synthesis and automating network diagnosis tasks, among others. In…
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for…
Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck: whether Large Language…
As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, code generation, and complex planning. Simultaneously, Multi-Agent Systems (MAS) have garnered attention for their potential to enable…
The emergence of Self-Driving Laboratories (SDLs) transforms scientific discovery methodology by integrating AI with robotic automation to create closed-loop experimental systems capable of autonomous hypothesis generation, experimentation,…
Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios…
In this case study, we describe the design and assembly of a cyber security testbed at Oak Ridge National Laboratory in Oak Ridge, TN, USA. The range is designed to provide agile reconfigurations to facilitate a wide variety of experiments…
Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against…
As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…
The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed…
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…
How well do AI systems perform in algorithm engineering for hard optimization problems in domains such as package-delivery routing, crew scheduling, factory production planning, and power-grid balancing? We introduce ALE-Bench, a new…
Context. Developing secure and reliable software remains a key challenge in software engineering (SE). The ever-evolving technological landscape offers both opportunities and threats, creating a dynamic space where chaos and order compete.…
AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…
As Large Language Models (LLMs) and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and researchers in the AI and cybersecurity communities are…