The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and its partner banks. Trust among these financial institutions is limited by regulation and competition. Federated learning (FL) enables entities to collaboratively train a model when data is either vertically or horizontally partitioned across the entities. However, in real-world financial anomaly detection scenarios, the data is partitioned both vertically and horizontally and hence it is not possible to use existing FL approaches in a plug-and-play manner. Our novel solution, PV4FAD, combines fully homomorphic encryption (HE), secure multi-party computation (SMPC), differential privacy (DP), and randomization techniques to balance privacy and accuracy during training and to prevent inference threats at model deployment time. Our solution provides input privacy through HE and SMPC, and output privacy against inference time attacks through DP. Specifically, we show that, in the honest-but-curious threat model, banks do not learn any sensitive features about PNS transactions, and the PNS does not learn any information about the banks' dataset but only learns prediction labels. We also develop and analyze a DP mechanism to protect output privacy during inference. Our solution generates high-utility models by significantly reducing the per-bank noise level while satisfying distributed DP. To ensure high accuracy, our approach produces an ensemble model, in particular, a random forest. This enables us to take advantage of the well-known properties of ensembles to reduce variance and increase accuracy. Our solution won second prize in the first phase of the U.S. Privacy Enhancing Technologies (PETs) Prize Challenge.

Widely available healthcare services are now getting popular because of advancements in wearable sensing techniques and mobile edge computing. People's health information is collected by edge devices such as smartphones and wearable bands for further analysis on servers, then send back suggestions and alerts for abnormal conditions. The recent emergence of federated learning allows users to train private data on local devices while updating models collaboratively. However, the heterogeneous distribution of the health condition data may lead to significant risks to model performance due to class imbalance. Meanwhile, as FL training is powered by sharing gradients only with the server, training data is almost inaccessible. The conventional solutions to class imbalance do not work for federated learning. In this work, we propose a new federated learning framework FedImT, dedicated to addressing the challenges of class imbalance in federated learning scenarios. FedImT contains an online scheme that can estimate the data composition during each round of aggregation, then introduces a self-attenuating iterative equivalent to track variations of multiple estimations and promptly tweak the balance of the loss computing for minority classes. Experiments demonstrate the effectiveness of FedImT in solving the imbalance problem without extra energy consumption and avoiding privacy risks.

Since the proposal of transformers, these models have been limited to bounded input lengths, because of their need to attend to every token in the input. In this work, we propose Unlimiformer: a general approach that wraps any existing pretrained encoder-decoder transformer, and offloads the cross-attention computation to a single k-nearest-neighbor (kNN) index, while the returned kNN distances are the attention dot-product scores. This kNN index can be kept on either the GPU or CPU memory and queried in sub-linear time; this way, we can index practically unlimited input sequences, while every attention head in every decoder layer retrieves its top-k keys, instead of attending to every key. We evaluate Unlimiformer on several long-document and book-summarization benchmarks, showing that it can process even 500k token-long inputs from the BookSum dataset, without any input truncation at test time. We demonstrate that Unlimiformer improves pretrained models such as BART and Longformer by extending them to unlimited inputs without additional learned weights and without modifying their code. We make our code and models publicly available at https://github.com/abertsch72/unlimiformer .

Focusing on doomsday scenarios in artificial intelligence is a distraction that plays down immediate risks such as the large-scale generation of misinformation, according to a senior industry figure attending this week's AI safety summit. Aidan Gomez, co-author of a research paper that helped create the technology behind chatbots, said long-term risks such as existential threats to humanity from AI should be "studied and pursued", but that they could divert politicians from dealing with immediate potential harms. "I think in terms of existential risk and public policy, it isn't a productive conversation to be had," he said. "As far as public policy and where we should have the public-sector focus – or trying to mitigate the risk to the civilian population – I think it forms a distraction, away from risks that are much more tangible and immediate." Gomez is attending the two-day summit, which starts on Wednesday, as chief executive of Cohere, a North American company that makes AI tools for businesses including chatbots.

Sounds like a tongue twister, doesn't it?" "What do you think you're doing?" shrieked Méndez's voice behind me. "What the fuck is going on with you?" I could tell that she was about to cry. I stopped the treadmill and got off carefully, without entirely disconnecting.

AI expert Marva Bailer explains how, even though there are currently laws in place, the average person has more access than ever to create deepfakes of celebrities. As artificial intelligence continues to gain popularity with individuals and companies, more stars are speaking out about its use. In an interview with The Associated Press, Cher expressed her fears about the technology after she heard someone use her voice to cover a song by Madonna. "Someone did me doing a Madonna song, and it was kind of shocking," she said. "They didn't have it down perfectly. But also, I've spent my entire life trying to be myself, and now these a--holes are going to go take it? And they'll do my acting, and they'll do my singing? WHAT IS ARTIFICIAL INTELLIGENCE (AI)? Cher said artificial intelligence is "out of control." She continued, "I'm telling you, if you work forever to become somebody -- and I'm not talking about somebody in the famous, money part -- but an artist, and then someone just takes it from you, it seems like it should be illegal." Marva Bailer, an AI expert, told Fox News Digital that stars do have legal recourse when it comes to unauthorized use of their likeness or voice. "The laws that exist in place are already – you need permission to use someone's likeness, and a likeness could be their song, their voice, their image or performance.

This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low latency. WikiChat is grounded on the English Wikipedia, the largest curated free-text corpus. WikiChat generates a response from an LLM, retains only the grounded facts, and combines them with additional information it retrieves from the corpus to form factual and engaging responses. We distill WikiChat based on GPT-4 into a 7B-parameter LLaMA model with minimal loss of quality, to significantly improve its latency, cost and privacy, and facilitate research and deployment. Using a novel hybrid human-and-LLM evaluation methodology, we show that our best system achieves 97.3% factual accuracy in simulated conversations. It significantly outperforms all retrieval-based and LLM-based baselines, and by 3.9%, 38.6% and 51.0% on head, tail and recent knowledge compared to GPT-4. Compared to previous state-of-the-art retrieval-based chatbots, WikiChat is also significantly more informative and engaging, just like an LLM. WikiChat achieves 97.9% factual accuracy in conversations with human users about recent topics, 55.0% better than GPT-4, while receiving significantly higher user ratings and more favorable comments.

We address an important gap in detecting political bias in news articles. Previous works that perform document classification can be influenced by the writing style of each news outlet, leading to overfitting and limited generalizability. Our approach overcomes this limitation by considering both the sentence-level semantics and the document-level rhetorical structure, resulting in a more robust and style-agnostic approach to detecting political bias in news articles. We introduce a novel multi-head hierarchical attention model that effectively encodes the structure of long documents through a diverse ensemble of attention heads. While journalism follows a formalized rhetorical structure, the writing style may vary by news outlet. We demonstrate that our method overcomes this domain dependency and outperforms previous approaches for robustness and accuracy. Further analysis and human evaluation demonstrate the ability of our model to capture common discourse structures in journalism. Our code is available at: https://github.com/xfactlab/emnlp2023-Document-Hierarchy

Do you support sustainability, social responsibility, tech ethics, or trust and safety? In his new self-published Techno-Optimist Manifesto, Andreessen presents his case for the advancement of technology under capitalism as "virtuous" and capable of creating "abundance that lifts all humans". Along the way he champions trickle-down economics (famously effective at increasing inequality), claims technology can solve any problem and suggests that slowing AI development is akin to murder. If you think such proposals sound divorced from reality, you're right. The harms of the state of technology are many: rampant surveillance, consolidation of power, bias and discrimination in automated decision-making systems, worsening power dynamics and labour conditions as a result of automation, and threats to creative workers from generative AI.

Maurice Funk, and co-authors Balder ten Cate, Jean Christoph Jung and Carsten Lutz, won a distinguished paper award at the 32nd International Joint Conference on Artificial Intelligence (IJCAI) for their work SAT-Based PAC Learning of Description Logic Concepts. In this interview, Maurice tells us more about knowledge bases and querying, why this is an interesting area for study, and their methodology and results. Our research is in the area of knowledge representation, or more specifically knowledge bases and querying. A knowledge base contains facts like a traditional database e.g. "Bob is a fish" and "Amelia is a dog", but also background knowledge formulated in some formal language e.g.