A Proposal for Evaluating the Operational Risk for ChatBots based on Large Language Models

The emergence of Generative AI (Gen AI) and Large Language Models (LLMs) has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend beyond traditional cybersecurity considerations. In this work, we propose a novel, instrumented risk-assessment metric that simultaneously evaluates potential threats to three key stakeholders: the service-providing organization, end users, and third parties. Our approach incorporates the technical complexity required to induce erroneous behaviors in the chatbot--ranging from non-induced failures to advanced prompt-injection attacks--as well as contextual factors such as the target industry, user age range, and vulnerability severity. To validate our metric, we leverage Garak, an open-source framework for LLM vulnerability testing. We further enhance Garak to capture a variety of threat vectors (e.g., misinformation, code hallucinations, social engineering, and malicious code generation). Our methodology is demonstrated in a scenario involving chatbots that employ retrieval-augmented generation (RAG), showing how the aggregated risk scores guide both short-term mitigation and longer-term improvements in model design and deployment. The results underscore the importance of multi-dimensional risk assessments in operationalizing secure, reliable AI-driven conversational systems.

Channel Independent Precoder for OFDM-based Systems over Fading Channels

In this paper we propose an independent channel precoder for orthogonal frequency division multiplexing (OFDM) systems over fading channels. The design of the precoder is based on the information redistribution of the input modulated symbols amongst the output precoded symbols. The proposed precoder decreases the variance of the instantaneous noise power at the receiver produced by the channel variability. The employment of an interleaver together with a precoding matrix whose size does not depend on the number of data carriers in an OFDM symbol allows different configurations of time-frequency diversity which can be easily adapted to the channel conditions. The precoder is evaluated with a modified Zero Forcing (ZF) equalizer whose maximum gain is constrained by means of a clipping factor. Thus, the clipping factor limits the noise power transfer in the receiver deprecoding block in low SNR conditions.