Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Throughout most of human history, the question "who deserves what?" could only be answered by

Russian authorities have returned the remains of 1,000 Ukrainian soldiers, Ukraine's Coordination Headquarters for the Treatment of Prisoners of War said on Monday, according to The Kyiv Independent news outlet. Russia's state-run TASS news agency confirmed that Russia returned the bodies of 1,000 soldiers, adding that Ukraine returned the bodies of 19 Russian soldiers. Separately, TASS reported that about 1,370 Ukrainian soldiers were killed in a single day, citing the Russian Ministry of Defence. Al Jazeera could not verify this claim independently. Russian forces dropped 250kg (550 lbs) bombs on the city of Kostiantynivka in Ukraine's Donetsk region, Serhii Horbunov, the head of the Kostiantynivka City Military Administration, wrote on Facebook on Monday.

DDoS attacks are one of the most prevalent and harmful cybersecurity threats faced by organizations and individuals today. In recent years, the complexity and frequency of DDoS attacks have increased significantly, making it challenging to detect and mitigate them effectively. The study analyzes various types of DDoS attacks, including volumetric, protocol, and application layer attacks, and discusses the characteristics, impact, and potential targets of each type. It also examines the existing techniques used for DDoS attack detection, such as packet filtering, intrusion detection systems, and machine learning-based approaches, and their strengths and limitations. Moreover, the study explores the prevention techniques employed to mitigate DDoS attacks, such as firewalls, rate limiting , CPP and ELD mechanism. It evaluates the effectiveness of each approach and its suitability for different types of attacks and environments. In conclusion, this study provides a comprehensive overview of the different types of DDoS attacks, their detection, and prevention techniques. It aims to provide insights and guidelines for organizations and individuals to enhance their cybersecurity posture and protect against DDoS attacks.

Federated Learning (FL) can be vulnerable to attacks, such as model poisoning, where adversaries send malicious local weights to compromise the global model. Federated Unlearning (FU) is emerging as a solution to address such vulnerabilities by selectively removing the influence of detected malicious contributors on the global model without complete retraining. However, unlike typical FU scenarios where clients are trusted and cooperative, applying FU with malicious and possibly colluding clients is challenging because their collaboration in unlearning their data cannot be assumed. This work presents FedUP, a lightweight FU algorithm designed to efficiently mitigate malicious clients' influence by pruning specific connections within the attacked model. Our approach achieves efficiency by relying only on clients' weights from the last training round before unlearning to identify which connections to inhibit. Isolating malicious influence is non-trivial due to overlapping updates from benign and malicious clients. FedUP addresses this by carefully selecting and zeroing the highest magnitude weights that diverge the most between the latest updates from benign and malicious clients while preserving benign information. FedUP is evaluated under a strong adversarial threat model, where up to 50%-1 of the clients could be malicious and have full knowledge of the aggregation process. We demonstrate the effectiveness, robustness, and efficiency of our solution through experiments across IID and Non-IID data, under label-flipping and backdoor attacks, and by comparing it with state-of-the-art (SOTA) FU solutions. In all scenarios, FedUP reduces malicious influence, lowering accuracy on malicious data to match that of a model retrained from scratch while preserving performance on benign data. FedUP achieves effective unlearning while consistently being faster and saving storage compared to the SOTA.

Speaker de-identification aims to conceal a speaker's identity while preserving intelligibility of the underlying speech. We introduce a benchmark that quantifies residual identity leakage with three complementary error rates: equal error rate, cumulative match characteristic hit rate, and embedding-space similarity measured via canonical correlation analysis and Procrustes analysis. Evaluation results reveal that all state-of-the-art speaker de-identification systems leak identity information. The highest performing system in our evaluation performs only slightly better than random guessing, while the lowest performing system achieves a 45% hit rate within the top 50 candidates based on CMC. These findings highlight persistent privacy risks in current speaker de-identification technologies.

The US Centers for Disease Control and Prevention (CDC), in 2019, designated Methicillin-resistant Staphylococcus au-reus (MRSA) as a serious antimicrobial resistance threat. The risk of acquiring MRSA and suffering life-threatening consequences due to it remains especially high for hospitalized patients due to a unique combination of factors, including: co-morbid conditions, immunosuppression, and antibiotic use, and risk of contact with contaminated hospital workers and equipment. In this paper, we present a novel generative probabilistic model, GenHAI, for modeling sequences of MRSA test results outcomes for patients during a single hospitalization. This model can be used to answer many important questions from the perspectives of hospital administrators for mitigating the risk of MRSA infections. Our model is based on the probabilistic programming paradigm, and can be used to approximately answer a variety of predictive, causal, and counterfactual questions. We demonstrate the efficacy of our model by comparing it against discriminative and generative machine learning models using two real world datasets.