Real-time trustworthiness evaluation and safety interception for AI agents. Semantic analysis, safe alternative suggestions, multi-step attack chain detection, and LLM-as-Judge.

Provides web credibility models (Likert scale) to assign a trustworthiness score to a given website.

Squeeze your model with pressure prompts to see if its behavior leaks.

In this paper, we introduce SAShA, a new attack strategy that leverages semantic features extracted from a knowledge graph in order to strengthen the efficacy of the attack to standard CF models. We performed an extensive experimental evaluation in order to investigate whether SAShA is more effective than baseline attacks against CF models by ta…

A Reliability-Aware Ingress Layer for Human Feedback in Stream Analytics

Codes and Datasets for our WSDM 2022 Paper: "MTLTS: A Multi-Task Framework To Obtain Trustworthy Summaries From Crisis-Related Microblogs"

Proposal of a novel adversarial attack approach, called Target Adversarial Attack against Multimedia Recommender Systems (TAaMR), to investigate the modification of MR behavior when the images of a category of low recommended products (e.g., socks) are perturbed to misclassify the deep neural classifier towards the class of more recommended prod…

Trust-gated smart-energy digital twin framework with uncertainty-aware decision support

An Assurance Process for Big Data Trustworthiness - Marco Anisetti, Claudio A. Ardagna, Filippo Berto

A module for monitoring and evaluating the trustworthiness of an Infrastructure Element of the Cloud-Edge-IoT continuum

In this work, we provide 24 combinations of attack/defense strategies, and visual-based recommenders to 1) access performance alteration on recommendation and 2) empirically verify the effect on final users through offline visual metrics.

REST API to insert messages into an IOTA Tangle