That time Oregon blew up a whale with dynamite. And why we should never do it again. Breakthroughs, discoveries, and DIY tips sent every weekday. When a whale dies in the ocean, an ecosystem grows around its sunken carcass. It's an epic burial at sea, something researchers call a whale fall .

At a time when nuclear threats feel more alarming than ever, Netflix's doomsday film falls frustratingly flat. A 1964 masterpiece tells a much better cautionary tale. Somewhere over the Arctic reaches of North America, a nuclear bomber flies in a squadron, awaiting its orders. When a secret code appears on a machine in the cockpit, the crew looks at each other, stunned. The code is instructing them to attack.

Large Language Models (LLMs) such as BERT [6] (Bidirectional Encoder Representations from Transformers) by Devlin et al. and GPT [11] (Generative Pre-trained Transformer) by Radford et al., have revolutionized the field of Natural Language Processing (NLP) with their exceptional capabilities, setting new standards in performance across various tasks. Due to their superb generative capability, LLMs are widely deployed as the backend for various real-world applications, referred to as LLM-Integrated Applications. For instance, Microsoft utilizes GPT-4 as the service backend for the new Bing Search [1]; OpenAI has developed various applications--such as ChatWithPDF and AskTheCode--that utilize GPT-4 for different tasks such as text processing, code interpretation, and product recommendation [2, 3]; Google deploys the search engine Bard, powered by PaLM 2. In general, to accomplish a task, an LLM-Integrated Application requires an instruction prompt, which aims to instruct the backend LLM to perform the task, and a data prompt, which is the data to be processed by the LLM in the task. The instruction prompt can be provided by a user or the LLM-Integrated Application itself; and the data prompt is often obtained from external resources such as emails and webpages on the Internet. An LLM-Integrated Application queries the backend LLM using the instruction prompt and data prompt to accomplish the task and returns the response from the LLM to the user. Recently, several types of vulnerabilities have been identified in LLMs to deceive models or mislead users. Among these, prompt injection attacks and jailbreak attacks stand out as prevalent vulnerabilities.

Federated Learning (FL) is a distributed learning paradigm that can coordinate heterogeneous edge devices to perform model training without sharing private data. While prior works have focused on analyzing FL convergence with respect to hyperparameters like batch size and aggregation frequency, the joint effects of adjusting these parameters on model performance, training time, and resource consumption have been overlooked, especially when facing dynamic data streams and network characteristics. This paper introduces novel analytical models and optimization algorithms that leverage the interplay between batch size and aggregation frequency to navigate the trade-offs among convergence, cost, and completion time for dynamic FL training. We establish a new convergence bound for training error considering heterogeneous datasets across devices and derive closed-form solutions for co-optimized batch size and aggregation frequency that are consistent across all devices. Additionally, we design an efficient algorithm for assigning different batch configurations across devices, improving model accuracy and addressing the heterogeneity of both data and system characteristics. Further, we propose an adaptive control algorithm that dynamically estimates network states, efficiently samples appropriate data batches, and effectively adjusts batch sizes and aggregation frequency on the fly. Extensive experiments demonstrate the superiority of our offline optimal solutions and online adaptive algorithm.