In recent years, knowledge distillation has become a cornerstone of efficiently deployed machine learning, with labs and industries using knowledge distillation to train models that are inexpensive and resource-optimized. Trojan attacks have contemporaneously gained significant prominence, revealing fundamental vulnerabilities in deep learning models. Given the widespread use of knowledge distillation, in this work we seek to exploit the unlabelled data knowledge distillation process to embed Trojans in a student model without introducing conspicuous behavior in the teacher. We ultimately devise a Trojan attack that effectively reduces student accuracy, does not alter teacher performance, and is efficiently constructible in practice. Neural networks often find themselves vulnerable to Trojan attacks, through which maliciously crafted inputs (i.e.

As a common situation in practice, the forecaster could access some additional resources which we call it side information, We study the effectiveness of stochastic side information in deterministic that may provide some useful knowledge on the online learning scenarios. We propose a forecaster sequence of interest. Cover and Ordentlich [10] first studied to predict a deterministic sequence where its performance is a portfolio investment problem where the sequence of interest evaluated against an expert class. We assume that certain is the stock vectors that may depend on some finite-valued stochastic side information is available to the forecaster but states (as side information), and their proposed forecaster can not the experts. We define the minimax expected regret for achieve the same wealth as the best side information dependent evaluating the forecaster's performance, for which we obtain investment strategy. Xie and Barron [11] studied the case when both upper and lower bounds. Consequently, our results characterize the sequence of interest is generated according to a pair-wise the improvement in the regret due to the stochastic parametric distribution conditioning on the side information, side information. Compared with the classical online learning and derived an logarithmic upper bound of the minimax regret.

With promising yet saturated results in high-resource settings, low-resource datasets have gradually become popular benchmarks for evaluating the learning ability of advanced neural networks (e.g., BigBench, superGLUE). Some models even surpass humans according to benchmark test results. However, we find that there exists a set of hard examples in low-resource settings that challenge neural networks but are not well evaluated, which causes over-estimated performance. We first give a theoretical analysis on which factors bring the difficulty of low-resource learning. It then motivate us to propose a challenging benchmark hardBench to better evaluate the learning ability, which covers 11 datasets, including 3 computer vision (CV) datasets and 8 natural language process (NLP) datasets. Experiments on a wide range of models show that neural networks, even pre-trained language models, have sharp performance drops on our benchmark, demonstrating the effectiveness on evaluating the weaknesses of neural networks. On NLP tasks, we surprisingly find that despite better results on traditional low-resource benchmarks, pre-trained networks, does not show performance improvements on our benchmarks. These results demonstrate that there are still a large robustness gap between existing models and human-level performance.

Implementing existing federated learning in massive Internet of Things (IoT) networks faces critical challenges such as imbalanced and statistically heterogeneous data and device diversity. To this end, we propose a semi-federated learning (SemiFL) framework to provide a potential solution for the realization of intelligent IoT. By seamlessly integrating the centralized and federated paradigms, our SemiFL framework shows high scalability in terms of the number of IoT devices even in the presence of computing-limited sensors. Furthermore, compared to traditional learning approaches, the proposed SemiFL can make better use of distributed data and computing resources, due to the collaborative model training between the edge server and local devices. Simulation results show the effectiveness of our SemiFL framework for massive IoT networks. The code can be found at https://github.com/niwanli/SemiFL_IoT.

Advanced large language models like ChatGPT have gained considerable attention recently, including among students. However, while the debate on ChatGPT in academia is making waves, more understanding is needed among lecturers and teachers on how students use and perceive ChatGPT. To address this gap, we analyzed the content on ChatGPT available on TikTok in February 2023. TikTok is a rapidly growing social media platform popular among individuals under 30. Specifically, we analyzed the content of the 100 most popular videos in English tagged with #chatgpt, which collectively garnered over 250 million views. Most of the videos we studied promoted the use of ChatGPT for tasks like writing essays or code. In addition, many videos discussed AI detectors, with a focus on how other tools can help to transform ChatGPT output to fool these detectors. This also mirrors the discussion among educators on how to treat ChatGPT as lecturers and teachers in teaching and grading. What is, however, missing from the analyzed clips on TikTok are videos that discuss ChatGPT producing content that is nonsensical or unfaithful to the training data.

While much research focused on producing explanations, it is still unclear how the produced explanations' quality can be evaluated in a meaningful way. Today's predominant approach is to quantify explanations using proxy scores which compare explanations to (human-annotated) gold explanations. This approach assumes that explanations which reach higher proxy scores will also provide a greater benefit to human users. In this paper, we present problems of this approach. Concretely, we (i) formulate desired characteristics of explanation quality, (ii) describe how current evaluation practices violate them, and (iii) support our argumentation with initial evidence from a crowdsourcing case study in which we investigate the explanation quality of state-of-the-art explainable question answering systems. We find that proxy scores correlate poorly with human quality ratings and, additionally, become less expressive the more often they are used (i.e. following Goodhart's law). Finally, we propose guidelines to enable a meaningful evaluation of explanations to drive the development of systems that provide tangible benefits to human users.

In the final chapter of Plagiarism in Higher Education: Tackling Tough Topics in Academic Integrity (2021) I contemplate the future of plagiarism and academic integrity. I introduced the idea of life in a postplagiarism world; thinking about the impact of artificial intelligence on writing. Here, I expand on those ideas. Hybrid writing, co-created by human and artificial intelligence together is becoming prevalent. Soon it will be the norm.

The story so far: Most of the discussion of ChatGPT I'm seeing from even very smart, tech-savvy people is just not good. In articles and podcasts, people are talking about this chatbot in unhelpful ways. And by "unhelpful ways," I don't just mean that they're anthropomorphizing (though they are doing that). Rather, what I mean is that they're not working with a practical, productive understanding of what the bot's main parts are and how they fit together. To put it another way, there are some can-opener problems manifesting in the ChatGPT conversation, and lowering the quality of The Discourse. To be clear, I do not know everything I'd like to know about this topic. That said, I'm certainly far enough along that I can help others who are a few steps behind.

To celebrate International Women's Day, we take a look back over the past year and highlight some of the women we've interviewed, written about, chatted to, and featured on AIhub. Rose Nakasi is a Lecturer of Computer Science and a Research Scientist at the Makerere Artificial Intelligence Lab, in Makerere University, Uganda. She holds a PhD in Computer Science from Makerere University. Her research interests are in artificial intelligence and data science, and particularly in the use of these for developing improved automated tools and techniques for microscopy diagnosis of diseases like malaria in low-resourced but highly endemic settings. We spoke to Rose Nakasi about her work developing machine learning techniques to aid diagnosis of microscopically diagnosed diseases: Interview with Rose Nakasi: using machine learning and smartphones to help diagnose malaria.

AI in the education system has been applied with a traditional approach for decades. On that note, computer-based teaching and learning programs were first developed in the 1960s. However, in the last few years, the presence of AI in schools and colleges has gradually become accepted as an effective tool for automating numerous tasks. For example, If students have questions about their schedule, chatbots can answer them. AI-generated emails remind students to register for classes, notify them of important deadlines, and turn in assignments.