The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks. These attacks exploit vulnerabilities within LLMs, endanger data integrity and user privacy. Guardrails serve as crucial protective mechanisms against such threats, but existing models often fall short in terms of both detection accuracy, and computational efficiency. This paper advocates for the significance of jailbreak attack prevention on LLMs, and emphasises the role of input guardrails in safeguarding these models. We introduce MoJE (Mixture of Jailbreak Expert), a novel guardrail architecture designed to surpass current limitations in existing state-of-the-art guardrails. By employing simple linguistic statistical techniques, MoJE excels in detecting jailbreak attacks while maintaining minimal computational overhead during model inference. Through rigorous experimentation, MoJE demonstrates superior performance capable of detecting 90% of the attacks without compromising benign prompts, enhancing LLMs security against jailbreak attacks.

Federated Learning (FL) has emerged as a powerful paradigm to train collaborative machine learning (ML) models, preserving the privacy of the participants’ datasets. However, standard FL approaches present some limitations that can hinder their applicability in some applications. Thus, the need of a server or aggregator to orchestrate the learning process may not be possible in scenarios with limited connectivity, as in some IoT applications, and offer less flexibility to personalize the ML models for the different participants. To sidestep these limitations, peer-to-peer FL (P2PFL) provides more flexibility, allowing participants to train their own models in collaboration with their neighbors. However, given the huge number of parameters of typical Deep Neural Network architectures, the communication burden can also be very high. On the other side, it has been shown that standard aggregation schemes for FL are very brittle against data and model poisoning attacks. In this paper, we propose SparSFA, an algorithm for P2PFL capable of reducing the communication costs. We show that our method outperforms competing sparsification methods in P2P scenarios, speeding the convergence and enhancing the stability during training. SparSFA also includes a mechanism to mitigate poisoning attacks for each participant in any random network topology. Our empirical evaluation on real datasets for intrusion detection in IoT, considering both balanced and imbalanced-dataset scenarios, shows that SparSFA is robust to different indiscriminate poisoning attacks launched by one or multiple adversaries, outperforming other robust aggregation methods whilst reducing the communication costs through sparsification.

We consider a communication scenario, in which an intruder tries to determine the modulation scheme of the intercepted signal. Our aim is to minimize the accuracy of the intruder, while guaranteeing that the intended receiver can still recover the underlying message with the highest reliability. This is achieved by perturbing channel input symbols at the encoder, similarly to adversarial attacks against classifiers in machine learning. In image classification, the perturbation is limited to be imperceptible to a human observer, while in our case the perturbation is constrained so that the message can still be reliably decoded by the legitimate receiver, which is oblivious to the perturbation. Simulation results demonstrate the viability of our approach to make wireless communication secure against state-of-the-art intruders (using deep learning or decision trees) with minimal sacrifice in the communication performance. On the other hand, we also demonstrate that using diverse training data and curriculum learning can significantly boost the accuracy of the intruder.

Data streams are a new class of data that is becoming pervasively important in a wide range of applications, ranging from sensor networks, environmental monitoring to finance. In this article, we propose a novel framework for the online diagnosis of evolution of multidimensional streaming data that incorporates Recursive Wavelet Density Estimators into the context of Velocity Density Estimation. In the proposed framework changes in streaming data are characterized by the use of local and global evolution coefficients . In addition, we propose for the analysis of changes in the correlation structure of the data a recursive implementation of the Pearson correlation coefficient using exponential discounting. Two visualization tools, namely temporal and spatial velocity profiles, are extended in the context of the proposed framework. These are the three main advantages of the proposed method over previous approaches: (1) the memory storage required is minimal and independent of any window size; (2) it has a significantly lower computational complexity; and (3) it makes possible the fast diagnosis of data evolution at all dimensions and at relevant combinations of dimensions with only one pass of the data. With the help of the four examples, we show the framework’s relevance in a change detection context and its potential capability for real world applications.