Related papers: Towards Provably Secure Generative AI: Reliable Co…

Quantifying uncertainty in automatically generated text is important for letting humans check potential hallucinations and making systems more reliable. Conformal prediction is an attractive framework to provide predictions imbued with…

The discriminative approach to classification using deep neural networks has become the de-facto standard in various fields. Complementing recent reservations about safety against adversarial examples, we show that conventional…

This paper proposes a Robust Safe Control Architecture (RSCA) for safe-decision making. The system to be controlled is a vehicle in the presence of bounded disturbances. The RSCA consists of two parts: a Supervisor MPC and a Controller MPC.…

The Robot Operating System (ROS) is a widely used framework for building robotic systems. It offers a wide variety of reusable packages and a pattern for new developments. It is up to developers how to combine these elements and integrate…

Designing distributed, fast and reliable wireless consensus protocols is instrumental in enabling mission-critical decentralized systems, such as robotic networks in the industrial Internet of Things (IIoT), drone swarms in rescue missions,…

Generative AI systems are increasingly used not only to produce content but also to retrieve data, invoke tools, and execute actions. This work examines the security and safety implications of that shift across content-level, model-level,…

Establishing trustworthy safety assurance for autonomous driving systems (ADSs) requires evidence that failures arise from avoidable system deficiencies rather than unavoidable traffic conflicts. Current adversarial simulation methods can…

We propose an approach for preventing unsafe or otherwise low-quality large language model (LLM) outputs by leveraging the stochasticity of LLMs, an approach we call Repeated Checking with Regeneration (RCR). In this system, LLM checkers…

It is widely known that state-of-the-art machine learning models, including vision and language models, can be seriously compromised by adversarial perturbations. It is therefore increasingly relevant to develop capabilities to certify…

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…

Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by prominent AI companies to deter model misuse have disincentives…

Respondent-driven sampling (RDS) is widely used to study hidden or hard-to-reach populations by incentivizing study participants to recruit their social connections. The success and efficiency of RDS can depend critically on the nature of…

Structured statistical estimation problems are often solved by Conditional Gradient (CG) type methods to avoid the computationally expensive projection operation. However, the existing CG type methods are not robust to data corruption. To…

This paper addresses novel consensus problems in the presence of adversaries that can move within the network and induce faulty behaviors in the attacked agents. By adopting several mobile adversary models from the computer science…

Mobile Crowdsensing systems are vulnerable to various attacks as they build on non-dedicated and ubiquitous properties. Machine learning (ML)-based approaches are widely investigated to build attack detection systems and ensure MCS systems…

Distributed consensus has been widely studied for sensor network applications. Whereas the asymptotic convergence rate has been extensively explored in prior work, other important and practical issues, including energy efficiency and link…

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

Reversible CCS (RCCS) is a well-established, formal model for reversible communicating systems, which has been built on top of the classical Calculus of Communicating Systems (CCS). In its original formulation, each CCS process is equipped…

Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by adjusting the sampling budget; however, they rely on…

This paper proposes probabilistic conformal prediction (PCP), a predictive inference algorithm that estimates a target variable by a discontinuous predictive set. Given inputs, PCP construct the predictive set based on random samples from…