arXiv:2602.06110v1 Announce Type: new Abstract: Machine learning in clinical settings must balance predictive accuracy, interpretability, and privacy. Models such as logistic regression (LR) offer transparency, while neural networks (NNs) provide greater predictive power; yet both remain vulnerable to privacy attacks. We empirically assess these risks by designing attacks that identify which public datasets were used to train a model under varying levels of adversarial access, applying them to LORIS, a publicly available LR model for immunotherapy response prediction, […]

Ver mais

Multi-label Class-Incremental Learning aims to continuously recognize novel categories in complex scenes where multiple objects co-occur. However, existing approaches often incur high computational costs due to full-parameter fine-tuning and substantial storage overhead from memory buffers, or they struggle to address feature confusion and domain discrepancies adequately. To overcome these limitations, we introduce P2L-CA, a parameter-efficient framework that integrates a Prompt-to-Label module with a Continuous Adapter module. The P2L module leverages class-specific prompts to disentangle multi-label representations while incorporating […]

Ver mais

In this quiz, you’ll test your understanding of the How to Use Google’s Gemini CLI for AI Code Assistance tutorial. By working through these questions, you’ll revisit how to install and verify prerequisites like Node.js, explore authentication options, and understand the CLI’s permission and safety model. You’ll also practice managing interactive sessions, enforcing stronger models, and approving or editing shell commands securely. To deepen your understanding, review the sections on verifying your environment, authenticating safely, and running interactive […]

Ver mais

arXiv:2602.02551v1 Announce Type: new Abstract: Transformer-based foundation models have achieved remarkable progress in tasks such as time-series forecasting and image segmentation. However, they frequently suffer from error accumulation in multivariate long-sequence prediction and exhibit vulnerability to out-of-distribution samples in image-related tasks. Furthermore, these challenges become particularly pronounced in large-scale Web data analysis tasks, which typically involve complex temporal patterns and multimodal features. This complexity substantially increases optimization difficulty, rendering models prone to stagnation at saddle points within high-dimensional […]

Ver mais

Detecting coordinated inauthentic behavior on social media remains a critical challenge, as many existing methods rely on correlation-based heuristics, fixed configurations, and heavy manual annotation. From the perspective of symmetry and asymmetry, coordinated campaigns often exhibit repeatable temporal and structural invariances (e.g., synchronized bursts and stable influence motifs), whereas adversarial adaptation and noisy environments introduce symmetry breaking and context-dependent deviations. To address this issue, we propose Adaptive Causal Coordination Detection (ACCD), a three-stage progressive framework with memory-guided adaptation. […]

Ver mais

arXiv:2601.16298v1 Announce Type: new Abstract: With the rise of decentralized finance, fiat-to-cryptocurrency exchange platforms have become popular entry points into the cryptocurrency ecosystem. However, these platforms frequently fail to ensure adequate privacy protection, as evidenced by real-world breaches that exposed personally identifiable information (PII) and crypto addresses. Such leaks enable adversaries to link real-world identities to cryptocurrency transactions, undermining the presumed anonymity of cryptocurrency use. We propose FC-GUARD, a privacy-preserving exchange system designed to preserve user anonymity without […]

Ver mais

arXiv:2502.01557v2 Announce Type: replace-cross Abstract: Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules can help mitigate these issues, finding optimal schedules is time-consuming and resource-intensive. This work explores theoretical issues concerning training stability in the constant-learning-rate (i.e., without schedule) and small-batch-size regime. Surprisingly, we show that the composition order of gradient updates affects stability and convergence in gradient-based optimizers. We illustrate this new […]

Ver mais

arXiv:2601.08012v1 Announce Type: new Abstract: Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records, which are unacceptable in enterprise contexts. Current approaches to mitigate these risks, such as model-based safeguards, enhance agents’ reliability but […]

Ver mais

We consider the problem of learning the optimal policy for Markov decision processes with safety constraints. We formulate the problem in a reach-avoid setup. Our goal is to design online reinforcement learning algorithms that ensure safety constraints with arbitrarily high probability during the learning phase. To this end, we first propose an algorithm based on the optimism in the face of uncertainty (OFU) principle. Based on the first algorithm, we propose our main algorithm, which utilizes entropy regularization. […]

Ver mais