Here's your daily roundup of the most relevant AI and ML news for September 09, 2026. Today's digest includes 1 security-focused story. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. U.S. Agencies Accuse China AI Firms of Distilling Claude, GPT, Gemini, and Grok
U.S. cybersecurity and intelligence agencies have accused China-based artificial intelligence (AI) companies of conducting "systematic extraction" of proprietary functionalities and capabilities of American frontier models through distillation attacks.
The activity has been described as occurrin...
Source: The Hacker News (Security) | 4 hours ago
Research & Papers
2. ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing
arXiv:2609.08256v1 Announce Type: cross Abstract: Automated red-team attacks and blue-team defenses for large language models (LLMs) are advancing quickly. However, attackers and defenders are built and tested in isolation, and the resulting scores are hard to trust. To tackle this, we present A...
Source: arXiv - AI | 10 hours ago
3. SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement
arXiv:2609.05850v1 Announce Type: new Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has revealed that LLMs remain vulnerable to adversarial jailbreak attacks that can bypass safety guardrails...
Source: arXiv - Machine Learning | 10 hours ago
4. Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
arXiv:2609.08236v1 Announce Type: new Abstract: Automatic safety judges -- systems such as Llama Guard or a GPT-4o grading prompt that decide whether a model's reply is harmful -- produce the numbers behind almost every reported jailbreak success rate, defense evaluation, and safety leaderboard....
Source: arXiv - AI | 10 hours ago
5. HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving
arXiv:2609.08306v1 Announce Type: cross Abstract: We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for in...
Source: arXiv - Machine Learning | 10 hours ago
6. Learning Without Adversarial Training: A Physics-Informed Neural Network for Secure Power System State Estimation under False Data Injection Attacks
arXiv:2604.22784v2 Announce Type: replace Abstract: Power System State Estimation (PSSE) converts geographically distributed measurements into the voltage magnitudes and phase angles needed for grid monitoring and control. Learned estimators can perform this mapping rapidly, but model-aware Fals...
Source: arXiv - Machine Learning | 10 hours ago
7. DART: Distributional Adversarial Recurrent Training for Algorithm Learning
arXiv:2609.05988v1 Announce Type: new Abstract: Recurrent reasoning models (RRMs) can solve structured problems, achieving easy-to-hard generalization through iterative computation in hidden space. These models are typically trained with instance-level supervision, which becomes increasingly pro...
Source: arXiv - Machine Learning | 10 hours ago
8. Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning
arXiv:2609.08683v1 Announce Type: new Abstract: Adversarial robustness in computer vision is still largely achieved through adversarial training or test-time adversarial purification, both of which introduce significant computational overhead by generating adversarial examples during training or...
Source: arXiv - Machine Learning | 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.