Related papers: NDAI Agreements
In recent years, artificial intelligence (AI) decision-making and autonomous systems became an integrated part of the economy, industry, and society. The evolving economy of the human-AI ecosystem raising concerns regarding the risks and…
Evidence lies at the core of litigation, but it is increasingly difficult to obtain in AI-related disputes. Even when a claimant's position has merit, cases are often settled or dismissed because decisive facts are hidden inside proprietary…
Edge Intelligence (EI) integrates Edge Computing (EC) and Artificial Intelligence (AI) to push the capabilities of AI to the network edge for real-time, efficient and secure intelligent decision-making and computation. However, EI faces…
The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…
AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and…
AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and financial information). This poses a serious risk to security and privacy.…
Modern AI systems are reaping the advantage of novel learning methods. With their increasing usage, we are realizing the limitations and shortfalls of these systems. Brittleness to minor adversarial changes in the input data, ability to…
The impact of designing for security of AI is critical for humanity in the AI era. With humans increasingly becoming dependent upon AI, there is a need for neural networks that work reliably, inspite of Adversarial attacks. The vision for…
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…
Training Data Attribution (TDA) seeks to trace model predictions back to influential training examples, enhancing interpretability and safety. We formulate TDA as a Bayesian information-theoretic problem: subsets are scored by the…
In non-truthful auctions, agents' utility for a strategy depends on the strategies of the opponents and also the prior distribution over their private types; the set of Bayes Nash equilibria generally has an intricate dependence on the…
The proliferation of autonomous AI agents represents a paradigmatic shift from traditional web architectures toward collaborative intelligent systems requiring sophisticated mechanisms for discovery, authentication, capability verification,…
We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification,…
Trusted Execution Environments (TEEs) protect confidentiality and integrity of trusted applications by creating an isolated environment for executing code. Prior work has shown that users may feel more comfortable sharing data when they…
AI-assisted task delegation is increasingly common, yet human effort in such systems is costly and typically unobserved. Recent work by Bastani and Cachon (2025); Sambasivan et al. (2021) shows that accuracy-based payment schemes suffer…
Methodologies for development of complex systems and models include external reviews by domain and technology experts. Among others, such reviews can uncover undocumented built-in assumptions that may be critical for correct and safe…
We study a continuous time economy where agents have asymmetric information. The informed agent (``$I$''), at time zero, receives a private signal about the risky assets' terminal payoff $\Psi(X_T)$, while the uninformed agent (``$U$'') has…
The field of artificial intelligence (AI) has experienced remarkable progress in recent years, driven by the widespread adoption of open-source machine learning models in both research and industry. Considering the resource-intensive nature…
We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past data as in classical induction, the objective is to capture…
This paper studies the role of hard information in contractual and market settings in which the receiver can flexibly adjust allocations and transfers in response to the sender's disclosure. These settings include monopoly pricing,…