Related papers: Coding against a Limited-view Adversary: The Effec…

Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel…

Space-time codes leverage the availability of multiple antennas to enhance the reliability of communication over wireless channels. While space-time codes have initially been designed with a focus on open-loop systems, recent technological…

An adversarial machine learning approach is introduced to launch jamming attacks on wireless communications and a defense strategy is presented. A cognitive transmitter uses a pre-trained classifier to predict the current channel status…

Preference-based feedback is important for many applications where direct evaluation of a reward function is not feasible. A notable recent example arises in reinforcement learning from human feedback on large language models. For many of…

Most practical communication links are bi-directional. In these models, since the source node also receives signals, its encoder has the option of computing its output based on the signals it received in the past. On the other hand, from a…

Adaptive coding faces the following problem: given a collection of source classes such that each class in the collection has non-trivial minimax redundancy rate, can we design a single code which is asymptotically minimax over each class in…

In this paper, we study network coding capacity for random wireless networks. Previous work on network coding capacity for wired and wireless networks have focused on the case where the capacities of links in the network are independent. In…

We revisit the problems of state masking and state amplification through the lens of empirical coordination. Specifically, we characterize the rate-equivocation-coordination trade-offs regions of a state-dependent channel in which the…

We consider synchronous dynamic networks which like radio networks may have asymmetric communication links, and are affected by communication rather than processor failures. In this paper we investigate the minimal message survivability in…

In predictive process monitoring, predictive models are vulnerable to adversarial attacks, where input perturbations can lead to incorrect predictions. Unlike in computer vision, where these perturbations are designed to be imperceptible to…

Modern large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities for coding tasks including writing and reasoning about code. They improve upon previous neural network models of code, such as code2seq or…

Causal additive models provide a tractable yet expressive framework for causal discovery in the presence of hidden variables. When unobserved backdoor or causal paths exist between two variables, their causal relationship is often…

We theoretically analyse the limits of robustness to test-time adversarial and noisy examples in classification. Our work focuses on deriving bounds which uniformly apply to all classifiers (i.e all measurable functions from features to…

We consider the scenario wherein Alice wants to (potentially) communicate to the intended receiver Bob over a network consisting of multiple parallel links in the presence of a passive eavesdropper Willie, who observes an unknown subset of…

Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, but important…

This paper presents a novel method for synthesizing new physical layer modulation and coding schemes for communications systems using a learning-based approach which does not require an analytic model of the impairments in the channel. It…

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional…

Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…

In a network, a channel introduces correlations to the parties that aim to establish a communication protocol. In this work, we present a framework of non-local network coding by exploiting a Bell scenario and show the usefulness of…

Adversarial attacks in the form of imperceptible perturbations of normal images have been extensively studied, and for every new defense methodology created, multiple adversarial attacks are found to counteract it. In particular, a popular…