Marine oil spills are urgent environmental hazards that demand rapid and reliable detection to minimise ecological and economic damage. While Synthetic Aperture Radar (SAR) imagery has become a key tool for large-scale oil spill monitoring, most existing detection methods rely on deep learning-based segmentation applied to single SAR images. These static approaches struggle to distinguish true oil spills from visually similar oceanic features (e.g., biogenic slicks or low-wind zones), leading to high false positive rates and limited generalizability, especially under data-scarce conditions. To overcome these limitations, we introduce Oil Spill Change Detection (OSCD), a new bi-temporal task that focuses on identifying changes between pre- and post-spill SAR images. As real co-registered pre-spill imagery is not always available, we propose the Temporal-Aware Hybrid Inpainting (TAHI) framework, which generates synthetic pre-spill images from post-spill SAR data. TAHI integrates two key components: High-Fidelity Hybrid Inpainting for oil-free reconstruction, and Temporal Realism Enhancement for radiometric and sea-state consistency. Using TAHI, we construct the first OSCD dataset and benchmark several state-of-the-art change detection models. Results show that OSCD significantly reduces false positives and improves detection accuracy compared to conventional segmentation, demonstrating the value of temporally-aware methods for reliable, scalable oil spill monitoring in real-world scenarios.
The rise of highly convincing synthetic speech poses a growing threat to audio communications. Although existing Audio Deepfake Detection (ADD) methods have demonstrated good performance under clean conditions, their effectiveness drops significantly under degradations such as packet losses and speech codec compression in real-world communication environments. In this work, we propose the first unified framework for robust ADD under such degradations, which is designed to effectively accommodate multiple types of Time-Frequency (TF) representations. The core of our framework is a novel Multi-Granularity Adaptive Attention (MGAA) architecture, which employs a set of customizable multi-scale attention heads to capture both global and local receptive fields across varying TF granularities. A novel adaptive fusion mechanism subsequently adjusts and fuses these attention branches based on the saliency of TF regions, allowing the model to dynamically reallocate its focus according to the characteristics of the degradation. This enables the effective localization and amplification of subtle forgery traces. Extensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art baselines across various real-world communication degradation scenarios, including six speech codecs and five levels of packet losses. In addition, comparative analysis reveals that the MGAA-enhanced features significantly improve separability between real and fake audio classes and sharpen decision boundaries. These results highlight the robustness and practical deployment potential of our framework in real-world communication environments.
Group-based reinforcement learning algorithms such as Group Reward Policy Optimization (GRPO) have proven effective for fine-tuning large language models (LLMs) with human feedback. However, generating and storing multiple responses per prompt incurs substantial memory overhead, especially as the sample group size increases, limiting scalability under constrained hardware. We propose Infinite Sampling, a framework that enables efficient and stable GRPO training by decoupling group size from GPU memory usage. It consists of: (1) micro sampling groups that decompose large groups into memory-feasible rounds; (2) continuous sampling that interleaves generation across groups to improve utilization; and (3) a length-aware scheduler combining token-conditioned sequence length prediction with a two-stage plan: global grouping via FPTAS and runtime refill via SJF. Experiments show that our Micro Sampling Groups reduce peak memory usage by over 50% compared to full-group decoding (e.g., from 21.55 GB to 10.64 GB on Qwen3-1.7B). Building on this, Infinite Sampling improves throughput by over 25% compared to the naive micro sampling group method, reducing decoding steps while maintaining full-length completions and memory usage. Our hybrid scheduling ensures efficient and stable GRPO training with larger groups under realistic GPU memory constraints.
Recent advances in Chain-of-Thought (CoT) prompting have substantially enhanced the reasoning capabilities of large language models (LLMs), enabling sophisticated problem-solving through explicit multi-step reasoning traces. However, these enhanced reasoning processes introduce novel attack surfaces, particularly vulnerabilities to computational inefficiency through unnecessarily verbose reasoning chains that consume excessive resources without corresponding performance gains. Prior overthinking attacks typically require restrictive conditions including access to external knowledge sources for data poisoning, reliance on retrievable poisoned content, and structurally obvious templates that limit practical applicability in real-world scenarios. To address these limitations, we propose POT (Prompt-Only OverThinking), a novel black-box attack framework that employs LLM-based iterative optimization to generate covert and semantically natural adversarial prompts, eliminating dependence on external data access and model retrieval. Extensive experiments across diverse model architectures and datasets demonstrate that POT achieves superior performance compared to other methods.