Supervised learning models are challenged by the intrinsic complexities of training data such as outliers and minority subpopulations and intentional attacks at inference time with adversarial samples. While traditional robust learning methods and the recent adversarial training approaches are designed to handle each of the two challenges, to date, no work has been done to develop models that are robust with regard to the low-quality training data and the potential adversarial attack at inference time simultaneously. It is for this reason that we introduce Outlier Robust Adversarial Training (ORAT) in this work. ORAT is based on a bi-level optimization formulation of adversarial training with a robust rank-based loss function. Theoretically, we show that the learning objective of ORAT satisfies the $\mathcal{H}$-consistency in binary classification, which establishes it as a proper surrogate to adversarial 0/1 loss. Furthermore, we analyze its generalization ability and provide uniform convergence rates in high probability. ORAT can be optimized with a simple algorithm. Experimental evaluations on three benchmark datasets demonstrate the effectiveness and robustness of ORAT in handling outliers and adversarial attacks. Our code is available at https://github.com/discovershu/ORAT.

Prior work has explicated the coloniality of artificial intelligence (AI) development and deployment. One process that that work has not engaged with much is alignment: the tuning of large language model (LLM) behavior to be in line with desired values based on fine-grained human feedback. In addition to other practices, colonialism has a history of altering the beliefs and values of colonized peoples; this history is recapitulated in current LLM alignment practices. We suggest that AI alignment be decolonialized using three proposals: (a) changing the base moral philosophy from Western philosophy to dharma, (b) permitting traditions of argument and pluralism in alignment technologies, and (c) expanding the epistemology of values beyond instructions or commandments given in natural language.

We present a novel approach for finding multiple noisily embedded template graphs in a very large background graph. Our method builds upon the graph-matching-matched-filter technique proposed in Sussman et al., with the discovery of multiple diverse matchings being achieved by iteratively penalizing a suitable node-pair similarity matrix in the matched filter algorithm. In addition, we propose algorithmic speed-ups that greatly enhance the scalability of our matched-filter approach. We present theoretical justification of our methodology in the setting of correlated Erdos-Renyi graphs, showing its ability to sequentially discover multiple templates under mild model conditions. We additionally demonstrate our method's utility via extensive experiments both using simulated models and real-world dataset, include human brain connectomes and a large transactional knowledge base.

Last week, WIRED published a deep-dive investigation into Trickbot, the prolific Russian ransomware gang. This week, US and UK authorities sanctioned 11 alleged members of Trickbot and its related group, Conti, including Maksim Galochkin, aka Bentley, one of the alleged members whose real-world identity we confirmed through our investigation. In addition to the US and UK sanctions, the US Justice Department also unsealed indictments filed in three US federal courts against Galochkin and eight other alleged Trickbot members for ransomware attacks against entities in Ohio, Tennessee, and California. Because everyone charged is a Russian national, however, it is unlikely they will ever be arrested or face trial. While Russian cybercriminals typically enjoy immunity, the same may not remain true for the country's military hackers.

The US government should create a new body to regulate artificial intelligence--and restrict work on language models like OpenAI's GPT-4 to companies granted licenses to do so. That's the recommendation of a bipartisan duo of senators, Democrat Richard Blumenthal and Republican Josh Hawley, who launched a legislative framework yesterday to serve as a blueprint for future laws and influence other bills before Congress. Under the proposal, developing face recognition and other "high risk" applications of AI would also require a government license. To obtain one, companies would have to test AI models for potential harm before deployment, disclose instances when things go wrong after launch, and allow audits of AI models by an independent third party. The framework also proposes that companies should publicly disclose details of the training data used to create an AI model, and that people harmed by AI get a right to bring the company that created it to court.

Deputy Secretary of Defense Kathleen Hicks addressed the plan and how the U.S. will continue to counter the rising aggression from China. The Pentagon has started to assess the possibility of developing an artificial intelligence (AI)-powered fleet of drones and autonomous systems that officials argue will allow the U.S. to compete with and counter threats from China. We are not seeking to be at war, but we have to be able to get this department to move with that same kind of urgency because the PRC isn't waiting," Kathleen Hicks, the deputy secretary of defense, said during an interview earlier this week with The Wall Street Journal. Hicks spoke about the potential uses of such an AI fleet during a speech on Wednesday, revealing the department would spend hundreds of millions of dollars on the project, aiming to produce thousands of systems for use over land, air and sea ready for first deployment within two years. China has focused heavily on AI research and development, producing ...

The COVID-19 pandemic belongs to the severest health, economic and social crises in recent decades and poses the greatest challenge to the world economy since World War II. The virus has spread around the globe and paralyzed entire economic sectors and activities. For economic modeling, the COVID-19 pandemic entails dealing with huge, unprecedented outliers in datasets which adversely affect the reliability of established, mostly linear, economic models. To the detriment of those commonly used models, economic indicators and variables are prone to unanticipated movements and do not respond in the way they are supposed to. Large shifts in the level of certain variables and strong deviations from their usual paths clearly aggravate the challenge of handling large outliers within existing econometric models.

Time-frequency analysis is an important and challenging task in many applications. Fourier and wavelet analysis are two classic methods that have achieved remarkable success in many fields. They also exhibit limitations when applied to nonlinear and non-stationary signals. To address this challenge, a series of nonlinear and adaptive methods, pioneered by the empirical mode decomposition method have been proposed. Their aim is to decompose a non-stationary signal into quasi-stationary components which reveal better features in the time-frequency analysis. Recently, inspired by deep learning, we proposed a novel method called residual recursive convolutional neural network (RRCNN). Not only RRCNN can achieve more stable decomposition than existing methods while batch processing large-scale signals with low computational cost, but also deep learning provides a unique perspective for non-stationary signal decomposition. In this study, we aim to further improve RRCNN with the help of several nimble techniques from deep learning and optimization to ameliorate the method and overcome some of the limitations of this technique.

Similar Narrative Retrieval is a crucial task since narratives are essential for explaining and understanding events, and multiple related narratives often help to create a holistic view of the event of interest. To accurately identify semantically similar narratives, this paper proposes a novel narrative similarity metric called Facet-based Narrative Similarity (FaNS), based on the classic 5W1H facets (Who, What, When, Where, Why, and How), which are extracted by leveraging the state-of-the-art Large Language Models (LLMs). Unlike existing similarity metrics that only focus on overall lexical/semantic match, FaNS provides a more granular matching along six different facets independently and then combines them. To evaluate FaNS, we created a comprehensive dataset by collecting narratives from AllSides, a third-party news portal. Experimental results demonstrate that the FaNS metric exhibits a higher correlation (37\% higher) than traditional text similarity metrics that directly measure the lexical/semantic match between narratives, demonstrating its effectiveness in comparing the finer details between a pair of narratives.

Large language models (LLMs) have shown promising performance on various NLP tasks via task prompting. And their performance can be further improved by appending task demonstrations to the head of the prompt. And usually, a better performance can be achieved with more demonstrations. However, asking the users to write the demonstrations can be cumbersome. As a simple yet cost-effective workaround, this paper proposes a novel method called EPA (\textbf{E}asy \textbf{P}rompt \textbf{A}ugmentation)\footnote{While this paper considers augmenting prompts via demonstrations, we name it EPA as the name EDA is already taken by a well-known NLP method \citep{wei-zou-2019-eda}.} that effectively minimizes user efforts in writing demonstrations while improving the model performance at the same time. EPA achieves these goals by automatically augmenting the demonstrations with multiple sources/targets, where each of them paraphrases each other. This is well motivated as augmenting data via paraphrasing effectively improves neural language models. EPA thus employs paraphrasing as an augmentation method for in-context learning. Extensive experiments indicate that EPA effectively improves both NLU and NLG tasks, covering from natural language inference to machine translation in translating tens of languages.\footnote{Code and data will be released upon publication.}