The generation of adversarial inputs has become a crucial issue in establishing the robustness and trustworthiness of deep neural nets, especially when they are used in safety-critical application domains such as autonomous vehicles and precision medicine. However, the problem poses multiple practical challenges, including scalability issues owing to large-sized networks, and the generation of adversarial inputs that lack important qualities such as naturalness and output-impartiality. This problem shares its end goal with the task of patching neural nets where small changes in some of the network’s weights need to be discovered so that upon applying these changes, the modified net produces the desirable output for a given set of inputs. We exploit this connection by proposing to obtain an adversarial input from a patch, with the underlying observation that the effect of changing the weights can also be brought about by changing the inputs instead. Thus, this paper presents a novel way to generate input perturbations that are adversarial for a given network by using an efficient network patching technique. We note that the proposed method is significantly more effective than the prior state-of-the-art techniques.

Communication among neurons is the highly evolved and efficient nanoscale communication paradigm, hence the most promising technique for biocompatible nanonetworks. This necessitates the understanding of neuro-spike communication from information theoretical perspective to reach a reference model for nanonetworks. This would also contribute towards developing ICT-based diagnostics techniques for neuro-degenerative diseases. Thus, in this paper, we focus on the fundamental building block of neuro-spike communication, i.e., signal transmission over a synapse, to evaluate its information transfer rate. We aim to analyze a realistic synaptic communication model, which for the first time, encompasses the variation in vesicle release probability with time, synaptic geometry and the re-uptake of neurotransmitters by pre-synaptic terminal. To achieve this objective, we formulate the mutual information between input and output of the synapse. Then, since this communication paradigm has memory, we evaluate the average mutual information over multiple transmissions to find its overall capacity. We derive a closed-form expression for the capacity of the synaptic communication as well as calculate the capacity-achieving input probability distribution. Finally, we find the effects of variation in different synaptic parameters on the information capacity and prove that the diffusion process does not decrease the information a neural response carries about the stimulus in real scenario.

Molecular communication (MC) is the most promising communication paradigm for nanonetwork realization since it is a natural phenomenon observed among living entities with nanoscale components. Since MC significantly differs from classical communication systems, it mandates reinvestigation of information and communication theoretical fundamentals. The closest examples of MC architectures are present inside our own body. Therefore, in this paper, we investigate the existing literature on intrabody nanonetworks and different MC paradigms to establish and introduce the fundamentals of molecular information and communication science. We highlight future research directions and open issues that need to be addressed for revealing the fundamental limits of this science. Although the scope of this development encompasses wide range of applications, we particularly emphasize its significance for life sciences by introducing potential diagnosis and treatment techniques for diseases caused by dysfunction of intrabody nanonetworks.