Here's your daily roundup of the most relevant AI and ML news for September 14, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Inverting Self-Triggered Control: Adversarial Reinforcement Learning for Sparse Denial-of-Service Attacks
arXiv:2609.12016v1 Announce Type: new Abstract: Self-triggered reinforcement learning control (RL-STC) learns the sparsest control schedule that preserves Lyapunov-decreasing stability under a Run-Time Assurance (RTA) override. We invert this: an adversarial RL agent learns the sparsest jamming ...
Source: arXiv - Machine Learning | 10 hours ago
2. Robust Policy Optimization via Adversarial Importance Sampling
arXiv:2609.13044v1 Announce Type: new Abstract: Significant progress has been made in safeguarding deep reinforcement learning (DRL) policies against input perturbations. Developing robust DRL involves three main stages: algorithm design, implementation, and evaluation. In this work, we identify...
Source: arXiv - Machine Learning | 10 hours ago
3. On Identifying Adversarial Intent Injection in AI-Native 6G Networks
arXiv:2609.12144v1 Announce Type: cross Abstract: AI-native 6G networks have brought Intent-Based Networking (IBN) to the forefront, enabling high-level goals to be translated into network configurations. However, this abstraction opens new attack surfaces, primarily adversarial intent injection...
Source: arXiv - Machine Learning | 10 hours ago
4. AI Safety: Not Optional, Not Later
arXiv:2609.10630v1 Announce Type: cross Abstract: Incidents show that AI safety failures often arise across multiple layers. We present a safety-by-design assurance architecture combining model-level supervision, such as Scientist AI, with system-level controls over scaffolds and harnesses, inde...
Source: arXiv - AI | 10 hours ago
5. Dissecting GPU Utilization for LLM Inference on Nvidia Hopper
arXiv:2609.12923v1 Announce Type: cross Abstract: A single SM utilization percentage can make an LLM inference workload look compute-saturated while hiding how much useful work is being done. The problem is not that the counter is wrong, but that it collapses several different mechanisms into on...
Source: arXiv - Machine Learning | 10 hours ago
6. CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
arXiv:2605.29271v2 Announce Type: replace-cross Abstract: Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the catalog uses technical API vocabulary that no fixed encoder can bridge on its own. The...
Source: arXiv - Machine Learning | 10 hours ago
7. Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks
arXiv:2501.04234v2 Announce Type: replace-cross Abstract: Modern artificial intelligence is supported by machine learning models (e.g., foundation models) that are pretrained on a massive data corpus and then adapted to solve a variety of downstream tasks. To summarize performance across multipl...
Source: arXiv - Machine Learning | 10 hours ago
8. Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges
arXiv:2609.01210v2 Announce Type: replace-cross Abstract: Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the response violates a policy. This distinction is critical in Chinese harmful-content evalu...
Source: arXiv - AI | 10 hours ago
About This Digest
This digest is automatically curated from leading AI and tech news sources, filtered for relevance to AI security and the ML ecosystem. Stories are scored and ranked based on their relevance to model security, supply chain safety, and the broader AI landscape.
Want to see how your favorite models score on security? Check our model dashboard for trust scores on the top 500 HuggingFace models.