Related papers: Synchronous Hybrid Message-Adversary
The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract…
We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…
A key motivation in the development of Distributed Model Predictive Control (DMPC) is to accelerate centralized Model Predictive Control (MPC) for large-scale systems. DMPC has the prospect of scaling well by parallelizing computations…
Bayesian inference on structured models typically relies on the ability to infer posterior distributions of underlying hidden variables. However, inference in implicit models or complex posterior distributions is hard. A popular tool for…
Robustness to Byzantine attacks is a necessity for various distributed training scenarios. When the training reduces to the process of solving a minimization problem, Byzantine robustness is relatively well-understood. However, other…
Distributed multi-task learning provides significant advantages in multi-agent networks with heterogeneous data sources where agents aim to learn distinct but correlated models simultaneously.However, distributed algorithms for learning…
While machine learning can accurately model process systems, models for decision making should also be structurally simple and physically interpretable. In process control, for example, (nearly) linear models are favored than nonlinear…
Fault-tolerant distributed systems offer high reliability because even if faults in their components occur, they do not exhibit erroneous behavior. Depending on the fault model adopted, hardware and software errors that do not result in a…
Many data management applications require integrating information from multiple sources. The sources may not be accurate and provide erroneous values. We thus have to identify the true values from conflicting observations made by the…
Generative adversarial networks (GANs) have been shown to produce realistic samples from high-dimensional distributions, but training them is considered hard. A possible explanation for training instabilities is the inherent imbalance…
Distributed algorithms that operate in the fail-recovery model rely on the state stored in stable memory to guarantee the irreversibility of operations even in the presence of failures. The performance of these algorithms lean heavily on…
Interactive consistency is the problem in which n nodes, where up to t may be byzantine, each with its own private value, run an algorithm that allows all non-faulty nodes to infer the values of each other node. This problem is relevant to…
Most research designing novel predictive models, or employing existing ones, assumes that training and testing data are independent and identically distributed. In practice, the data encountered at serving time often deviate from the…
A network of observers is considered, where through asynchronous (with bounded delay) communications, they cooperatively estimate the states of a Linear Time-Invariant (LTI) system. In such a setting, a new type of adversary might affect…
We conduct a systematic study of asynchronous models of distributed computing consisting of identical finite-state devices that cooperate in a network to decide if the network satisfies a given graph-theoretical property. Models discussed…
In a recent paper, Jaggi et al. (INFOCOM 2007), presented a distributed polynomial-time rate-optimal network-coding scheme that works in the presence of Byzantine faults. We revisit their adversarial models and augment them with three,…
Nowadays, both the amount of cyberattacks and their sophistication have considerably increased, and their prevention is of concern of most of organizations. Cooperation by means of information sharing is a promising strategy to address this…
In distributed learning systems, robustness issues may arise from two sources. On one hand, due to distributional shifts between training data and test data, the trained model could exhibit poor out-of-sample performance. On the other hand,…
Recent work showed that hybrid networks, which combine predefined and learnt filters within a single architecture, are more amenable to theoretical analysis and less prone to overfitting in data-limited scenarios. However, their performance…
This report contains two related sets of results with different assumptions on synchrony. The first part is about iterative algorithms in synchronous systems. Following our previous work on synchronous iterative approximate Byzantine…