Related papers: Full-Life Cycle Intent-Driven Network Verification…

The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed…

We present Conformal Intent Classification and Clarification (CICC), a framework for fast and accurate intent classification for task-oriented dialogue systems. The framework turns heuristic uncertainty scores of any intent classifier into…

Ensuring the safety of reinforcement learning (RL) policies in high-stakes environments requires not only formal verification but also interpretability and targeted falsification. While model checking provides formal guarantees, its…

Being a state-of-the-art network, Software Defined Networking (SDN) decouples control and management planes from data plane of the forwarding devices by implementing both the control and management planes at logically centralized entity,…

Distributed quantum information in networks is paramount for global secure quantum communication. Moreover, it finds applications as a resource for relevant tasks, such as clock synchronization, magnetic field sensing, and blind quantum…

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…

Networks represent relationships between entities in many complex systems, spanning from online social interactions to biological cell development and brain connectivity. In many cases, relationships between entities are unambiguously…

We envision future mobile networks to be human-centric supporting interest-aware delivery, where an interest maybe based on behavior, such as mobility pattern, location, or web browsing (or user profile) such as affiliation, attributes, or…

With the growing deployment of Vision-Language Models (VLMs) in real-world applications, previously overlooked safety risks are becoming increasingly evident. In particular, seemingly innocuous multimodal inputs can combine to reveal…

To achieve reliable, robust, and safe AI systems, it is vital to implement fallback strategies when AI predictions cannot be trusted. Certifiers for neural networks are a reliable way to check the robustness of these predictions. They…

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Internet-of-Things (IoT) devices are increasingly common in both consumer and industrial settings, often performing safety-critical functions. Although securing these devices is vital, manufacturers typically neglect security issues or…

Intent detection is a critical component of task-oriented dialogue systems (TODS) which enables the identification of suitable actions to address user utterances at each dialog turn. Traditional approaches relied on computationally…

Recommender systems take inputs from user history, use an internal ranking algorithm to generate results and possibly optimize this ranking based on feedback. However, often the recommender system is unaware of the actual intent of the user…

This paper addresses the problem of formally verifying desirable properties of neural networks, i.e., obtaining provable guarantees that neural networks satisfy specifications relating their inputs and outputs (robustness to bounded norm…

In the current control design of safety-critical autonomous systems, formal verification techniques are typically applied after the controller is designed to evaluate whether the required properties (e.g., safety) are satisfied. However,…

Modern machine learning models are sensitive to the manipulation of both the training data (poisoning attacks) and inference data (adversarial examples). Recognizing this issue, the community has developed many empirical defenses against…

Deep neural networks can be trained to be efficient and effective controllers for dynamical systems; however, the mechanics of deep neural networks are complex and difficult to guarantee. This work presents a general approach for providing…

Fairness in machine learning is more important than ever as ethical concerns continue to grow. Individual fairness demands that individuals differing only in sensitive attributes receive the same outcomes. However, commonly used machine…

This work presents a model-based development methodology for verified software systems as well as a tool support for it: an applied AutoFocus tool chain and its basic principles emphasizing the verification of the system under development…