Building Trust

Building Trust in Black-box Optimization: A Comprehensive Framework for Explainability

Announce Type: replace Abstract: Optimizing costly black-box functions within a constrained evaluation budget presents significant challenges in many real-world applications. Surrogate Optimization (SO) is a common resolution, yet its proprietary nature introduced by the complexity of surrogate models and the sampling core (e.g., acquisition functions) often leads to a lack of explainability and transparency. While existing literature has primarily concentrated on enhancing convergence to...

‘A sense of trusting one’s self’: how to start building confidence

TeeDAO: A Decentralized Autonomous Organization for Heterogeneous TEEs

Announce Type: new Abstract: Trusted Execution Environments (TEEs) have emerged as a critical technology for safeguarding sensitive data and ensuring code integrity in modern computing systems. However, relying on a single TEE implementation makes systems vulnerable to a central point of attack. Building distributed-trust systems leveraging heterogeneous TEEs helps disperse trust but still faces threats from centralized management and adaptive mobile adversaries.

5 Tips to Start Managing Your Aging Parents’ Money

Cathleen Tobin, a financial planner, has been assisting her father, Ed, with his money. “Helping your parents in small ways builds trust and normalizes your involvement,” she said.

Noise Inference by Recycling Test Rounds in Verification Protocols

Announce Type: replace-cross Abstract: Interactive verification protocols for quantum computations allow to build trust between a client and a service provider, ensuring the former that the instructed computation was carried out faithfully. They come in two variants, one without quantum communication that requires large overhead on the server side to coherently implement quantum-resistant cryptographic primitives, and one with quantum communication but with repetition as the only overhead on...

"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory

arXiv:2606.08076v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored. This work explores the persuasive potential of LLMs through the framework of J\"urgen Habermas' Theory of Communicative Action. It examines whether LLMs express illocutionary intent (i.e., pragmatic functions of language such as conveying knowledge, building trust, or signaling...

Trump says will not unfreeze Iranian assets before ceasefire deal reached

Trump says will not unfreeze Iranian assets before ceasefire deal reached Iranian officials have indicated the release of funds would build ‘trust’ needed to reach lasting deal ending war. United States President Donald Trump has said he will not unfreeze billions of dollars in Iranian assets prior to a lasting ceasefire agreement being reached to formally end the US-Israel war with Iran. Trump made the statement in an interview on the NBC News programme Meet the Press that aired on Sunday,...

Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory

Announce Type: replace Abstract: AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events. A concession during a client negotiation encodes as a ``trust-building investment'' for one strategic goal and a ``contractual liability'' for another. Current memory architectures assume a single correct encoding, or at best support multiple views over unified storage.

Towards interpretable AI with quantum annealing feature selection

arXiv:2604.25649v2 Announce Type: replace Abstract: Deep learning models are used in critical applications, in which mistakes can have serious consequences. Therefore, it is crucial to understand how and why models generate predictions. This understanding provides useful information to check whether the model is learning the right patterns, detect biases in the data, improve model design, and build systems that can be trusted.

Why Iran fears a deal today means more war tomorrow

The article discusses Iran's concerns about the US's concessions in the nuclear deal, which Tehran interprets as too good to be true. The author argues that Iran's fears are rooted in its history of being deceived by the US, and that the concessions may lead to more war in the future. The article highlights the complexities of the nuclear deal and the challenges of building trust between the two nations. Note: The summary is based on the provided article and is intended to be a concise and factual representation of the main points.