Related papers: Security awareness in LLM agents: the NDAI zone ca…
AI agents, empowered by Large Language Models (LLMs) and communication protocols such as MCP and A2A, have rapidly evolved from simple chatbots to autonomous entities capable of executing complex, multi-step tasks, demonstrating great…
Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…
Trusted Execution Environments (TEEs) provide hardware-enforced isolation that protects sensitive code and data from untrusted software. Despite their strong security guarantees, analyzing TEE applications remains challenging due to the…
Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues such as names, locations, and cultural stereotypes, rather than the underlying…
Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…
Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static…
Large language model-based (LLM-based) agents have become common in settings that include non-cooperative parties. In such settings, agents' decision-making needs to conceal information from their adversaries, reveal information to their…
Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…
Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during…
In this paper, we address the problems faced by a group of agents that possess situational awareness, but lack a security mechanism, by the introduction of a adaptive risk management system. The Belief-Desire-Intention (BDI) architecture…
LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging…
Negotiation is a central mechanism of economic exchange, shaping markets, procurement, labor agreements, and resource allocation. It is also a canonical testbed for agentic language models, requiring multi-turn interaction under hidden…
The transition of Large Language Models (LLMs) from passive code generators to autonomous agents introduces significant safety risks, specifically regarding destructive commands and inconsistent system states. Existing commercial solutions…
In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the…
Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…
Trust in AI agents has been extensively studied in the literature, resulting in significant advancements in our understanding of this field. However, the rapid advancements in Large Language Models (LLMs) and the emergence of LLM-based AI…
Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often…
Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…
Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms. However, the defect of recommendation algorithms may put users in very…
The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems, leading to the prevalence of AI-generated content and challenges in detecting misinformation and managing…