Related papers: EigenAI: Deterministic Inference, Verifiable Resul…
AI systems increasingly shape critical decisions across personal and societal domains. While empirical risk minimization (ERM) drives much of the AI success, it typically prioritizes accuracy over trustworthiness, often resulting in biases,…
Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and…
Generative Artificial Intelligence (GenAI) applies models and algorithms such as Large Language Model (LLM) and Foundation Model (FM) to generate new data. GenAI, as a promising approach, enables advanced capabilities in various…
Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural network (DNN) inference are offloaded to external participants due to blockchain limitations. This…
Bitcoin and Ethereum, whose miners arguably collectively comprise the most powerful computational resource in the history of mankind, offer no more power for processing and verifying transactions than a typical smart phone. The system…
Artificial intelligence (AI) is becoming increasingly more popular and can be found in workplaces and homes around the world. The decisions made by such "black box" systems are often opaque; that is, so complex as to be functionally…
We introduce CheckNet, a method for secure inference with deep neural networks on untrusted devices. CheckNet is like a checksum for neural network inference: it verifies the integrity of the inference computation performed by untrusted…
Eigentrust is a simple and widely used algorithm, which quantifies trust based on the repeated application of an update matrix to a vector of initial trust values. In some cases, however, this procedure is rendered uninformative. Here, we…
The transition of Ethereum from a Proof-of-Work (PoW) to a Proof-of-Stake (PoS) consensus mechanism introduces a transformative approach to blockchain validation, offering enhanced scalability, energy efficiency, and security. However, this…
Introducing Reliablocks, an on-chain reliability index for non-finalized blocks in Optimistic Rollups. This was built during the EigenLayer Infinite Hackathon at the Infinite Hacker House at DevCon 2024. As part of this research, we…
Machine unlearning updates machine learning models to remove information from specific training samples, complying with data protection regulations that allow individuals to request the removal of their personal data. Despite the recent…
Generative artificial intelligence now synthesizes photorealistic imagery, audio, and video at a cost that defeats traditional forensic intuition. The legal consequences span three regimes studied so far in isolation: international…
In this paper, we introduce the VerifAI project, a pioneering open-source scientific question-answering system, designed to provide answers that are not only referenced but also automatically vetted and verifiable. The components of the…
Generative Artificial Intelligence (GenAI) has demonstrated its capabilities in the present world that reduce human effort significantly. It utilizes deep learning techniques to create original and realistic content in terms of text,…
As cyber threats continue to evolve, securing edge networks has become increasingly challenging due to their distributed nature and resource limitations. Many AI-driven threat detection systems rely on complex deep learning models, which,…
Artificial Intelligence (AI) is becoming the corner stone of many systems used in our daily lives such as autonomous vehicles, healthcare systems, and unmanned aircraft systems. Machine Learning is a field of AI that enables systems to…
As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…
This study explores the application of generative AI (GenAI) within manual exploitation and privilege escalation tasks in Linux-based penetration testing environments, two areas critical to comprehensive cybersecurity assessments. Building…
Distributed ledger systems (i.e., blockchains) have received a lot of attention. They promise to enable mutually untrusted participants to execute transactions while providing the immutability of the data and censorship resistance. Although…
Recent advances in Transformer models, e.g., large language models (LLMs), have brought tremendous breakthroughs in various artificial intelligence (AI) tasks, leading to their wide applications in many security-critical domains. Due to…