For the second time in nearly two weeks, the United States carried out airstrikes against a facility used by Iran's Islamic Revolutionary Guards Corps and its proxies in eastern Syria early Thursday, ratcheting up retaliation for a steady stream of rocket and drone attacks against American forces in Iraq and Syria. The strikes by two Air Force F-15E jets against a weapons warehouse in Deir al Zour Province, Syria, came after U.S. airstrikes on Oct. 27 against similar targets in eastern Syria failed to deter Iran or its proxies in Syria and Iraq, which the Biden administration has blamed for the attacks. Not only have the attacks continued -- there have been at least 22 more since the American retaliatory strikes last month -- but Pentagon officials said they have become more dangerous. Iran-backed militias have packed even larger loads of explosives -- more than 80 pounds -- onto drones launched at American bases, U.S. officials said. "This precision self-defense strike is a response to a series of attacks against U.S. personnel in Iraq and Syria by I.R.G.C.-Quds Force affiliates," Defense Secretary Lloyd J. Austin III said in a statement.

This post contains a list of the AI-related seminars that are scheduled to take place between 10 November and 31 December 2023. All events detailed here are free and open for anyone to attend virtually. Instrumental Time Series and Effect-Invariance for Policy Generalization Speaker: Jonas Peters (ETHZ) Organised by: UCL ELLIS Zoom link is here. Empowering Africa's Health Research Through Data Sharing and Governance Speaker: Lukman Enegi Ismaila Organised by: Lanfrica The Zoom link is here. Title to be confirmed Speaker: William Fedus (OpenAI) Organised by: Stanford MLSys Check the website nearer the time for the livestream link.

The announcement comes a day after Microsoft announced it was also taking a number of steps to protect elections, including offering tools to watermark AI-generated content and deploying a "Campaign Success Team" to advise political campaigns on AI, cybersecurity, and other related issues. Next year will be the most significant year for elections so far this century, with the U.S., India, the U.K., Mexico, Indonesia, and Taiwan all headed to the polls. Although many are concerned about the impact deepfakes and misinformation could have on elections, many experts stress the evidence for their impacts on elections so far is limited at best. Experts welcome the measures taken by tech companies to defend election integrity but say more fundamental changes to political systems will be required to tackle misinformation. Tech companies have come under scrutiny after the role they played in previous elections.

A U.S. military surveillance drone was shot down off the coast of Yemen on Wednesday by Iran-backed Houthi rebels, the Pentagon said. Pentagon officials, speaking on the condition of anonymity to discuss operational matters, confirmed that the drone, an MQ-9 Reaper, had been shot down. But they would not say if the aircraft was armed, where it was flying from or other details. The downing of a Reaper drone, the mainstay of the American military's aerial surveillance fleet, was the latest escalation of violence between the United States and Iran-backed groups in Yemen, Iraq and Syria. The episodes have underscored the risks that the conflict between Israel and the Palestinian group Hamas could spiral into a wider war.

We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing each example by a vector consisting of the answers to these questions. We call this representation Natural Language Learned Features (NLLF). NLLF is generated by a small transformer language model (e.g., BERT) that has been trained in a Natural Language Inference (NLI) fashion, using weak labels automatically obtained from a Large Language Model (LLM). We show that the LLM normally struggles for the main task using in-context learning, but can handle these easiest subtasks and produce useful weak labels to train a BERT. The NLI-like training of the BERT allows for tackling zero-shot inference with any binary question, and not necessarily the ones seen during the training. We show that this NLLF vector not only helps to reach better performances by enhancing any classifier, but that it can be used as input of an easy-to-interpret machine learning model like a decision tree. This decision tree is interpretable but also reaches high performances, surpassing those of a pre-trained transformer in some cases.We have successfully applied this method to two completely different tasks: detecting incoherence in students' answers to open-ended mathematics exam questions, and screening abstracts for a systematic literature review of scientific papers on climate change and agroecology.

Despite the impressive performance of current AI models reported across various tasks, performance reports often do not include evaluations of how these models perform on the specific groups that will be impacted by these technologies. Among the minority groups under-represented in AI, data from low-income households are often overlooked in data collection and model evaluation. We evaluate the performance of a state-of-the-art vision-language model (CLIP) on a geo-diverse dataset containing household images associated with different income values (Dollar Street) and show that performance inequality exists among households of different income levels. Our results indicate that performance for the poorer groups is consistently lower than the wealthier groups across various topics and countries. We highlight insights that can help mitigate these issues and propose actionable steps for economic-level inclusive AI development. Code is available at https://github.com/MichiganNLP/Bridging_the_Digital_Divide.

Cyber attacks are often identified using system and network logs. There have been significant prior works that utilize provenance graphs and ML techniques to detect attacks, specifically advanced persistent threats, which are very difficult to detect. Lately, there have been studies where transformer-based language models are being used to detect various types of attacks from system logs. However, no such attempts have been made in the case of APTs. In addition, existing state-of-the-art techniques that use system provenance graphs, lack a data processing framework generalized across datasets for optimal performance. For mitigating this limitation as well as exploring the effectiveness of transformer-based language models, this paper proposes LogShield, a framework designed to detect APT attack patterns leveraging the power of self-attention in transformers. We incorporate customized embedding layers to effectively capture the context of event sequences derived from provenance graphs. While acknowledging the computational overhead associated with training transformer networks, our framework surpasses existing LSTM and Language models regarding APT detection. We integrated the model parameters and training procedure from the RoBERTa model and conducted extensive experiments on well-known APT datasets (DARPA OpTC and DARPA TC E3). Our framework achieved superior F1 scores of 98% and 95% on the two datasets respectively, surpassing the F1 scores of 96% and 94% obtained by LSTM models. Our findings suggest that LogShield's performance benefits from larger datasets and demonstrates its potential for generalization across diverse domains. These findings contribute to the advancement of APT attack detection methods and underscore the significance of transformer-based architectures in addressing security challenges in computer systems.

Understanding event descriptions is a central aspect of language processing, but current approaches focus overwhelmingly on single sentences or documents. Aggregating information about an event \emph{across documents} can offer a much richer understanding. To this end, we present FAMuS, a new corpus of Wikipedia passages that \emph{report} on some event, paired with underlying, genre-diverse (non-Wikipedia) \emph{source} articles for the same event. Events and (cross-sentence) arguments in both report and source are annotated against FrameNet, providing broad coverage of different event types. We present results on two key event understanding tasks enabled by FAMuS: \emph{source validation} -- determining whether a document is a valid source for a target report event -- and \emph{cross-document argument extraction} -- full-document argument extraction for a target event from both its report and the correct source article. We release both FAMuS and our models to support further research.

Pre-trained language models (PLMs) have recently shown great success in text representation field. However, the high computational cost and high-dimensional representation of PLMs pose significant challenges for practical applications. To make models more accessible, an effective method is to distill large models into smaller representation models. In order to relieve the issue of performance degradation after distillation, we propose a novel Knowledge Distillation method called IBKD. This approach is motivated by the Information Bottleneck principle and aims to maximize the mutual information between the final representation of the teacher and student model, while simultaneously reducing the mutual information between the student model's representation and the input data. This enables the student model to preserve important learned information while avoiding unnecessary information, thus reducing the risk of over-fitting. Empirical studies on two main downstream applications of text representation (Semantic Textual Similarity and Dense Retrieval tasks) demonstrate the effectiveness of our proposed approach.

Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks. Recent methods employ expensive retraining or attempt debiasing during inference by constraining model outputs to contrast from a reference set of biased templates or exemplars. Regardless, they dont address the primary goal of fairness to maintain equitability across different demographic groups. In this work, we posit that inferencing LMs to generate unbiased output for one demographic under a context ensues from being aware of outputs for other demographics under the same context. To this end, we propose Counterfactually Aware Fair InferencE (CAFIE), a framework that dynamically compares the model understanding of diverse demographics to generate more equitable sentences. We conduct an extensive empirical evaluation using base LMs of varying sizes and across three diverse datasets and found that CAFIE outperforms strong baselines. CAFIE produces fairer text and strikes the best balance between fairness and language modeling capability