Related papers: Corrigibility with Utility Preservation
For flexible yet safe imitation learning (IL), we propose theory and a modular method, with a safety layer that enables a closed-form probability density/gradient of the safe generative continuous policy, end-to-end generative adversarial…
Autonomous agents powered by large language models (LLMs) enable novel use cases in domains where responsible action is increasingly important. Yet the inherent unpredictability of LLMs raises safety concerns about agent reliability. In…
A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has…
This paper presents the Artificial Agency Program (AAP), a position and research agenda for building AI systems as reality embedded, resource-bounded agents whose development is driven by curiosity-as-learning-progress under physical and…
Research in Artificial Intelligence is breaking technology barriers every day. New algorithms and high performance computing are making things possible which we could only have imagined earlier. Though the enhancements in AI are making life…
Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…
Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…
Agentic systems have transformed how Large Language Models (LLMs) can be leveraged to create autonomous systems with goal-directed behaviors, consisting of multi-step planning and the ability to interact with different environments. These…
The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these deficiencies, we propose a principled engineering framework…
We consider the safe reinforcement learning (RL) problem of maximizing utility with extremely low constraint violation rates. Assuming no prior knowledge or pre-training of the environment safety model given a task, an agent has to learn,…
From early days, a key and controversial question inside the artificial intelligence community was whether Artificial General Intelligence (AGI) is achievable. AGI is the ability of machines and computer programs to achieve human-level…
Securing AI agents powered by Large Language Models (LLMs) represents one of the most critical challenges in AI security today. Unlike traditional software, AI agents leverage LLMs as their "brain" to autonomously perform actions via…
Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. In this study, we investigate…
Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…
The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…
Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces visually. Yet supervised fine-tuning alone cannot handle long-horizon credit assignment,…
The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user objectives, violate data handling policies, or be compromised by…
Authorship Verification (AV) is a text classification task concerned with inferring whether a candidate text has been written by one specific author or by someone else. It has been shown that many AV systems are vulnerable to adversarial…
Although Retrieval-Augmented Generation (RAG) systems have been widely applied, the privacy and security risks they face, such as data leakage and data poisoning, have not been systematically addressed yet. Existing defense strategies…