Here's your daily roundup of the most relevant AI and ML news for September 15, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion
arXiv:2609.13511v1 Announce Type: new Abstract: Large language models are increasingly benchmarked against classical machine learning for network intrusion detection (NIDS), almost always using same-dataset evaluation, and that protocol turns out to be incomplete. Evaluating XGBoost and RoBERTa-...
Source: arXiv - Machine Learning | 10 hours ago
2. ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents
arXiv:2609.14987v1 Announce Type: cross Abstract: Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect prompt injection (IPI) attacks. Existing defenses mainly rely on prompt hardening, content filtering,...
Source: arXiv - AI | 10 hours ago
3. Fusing Spectral Signatures and Activation Clustering for Backdoor Detection in Healthcare Imaging Models: Method, Implementation, and Evaluation
arXiv:2609.14290v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in healthcare imaging pipelines for diagnostic support, and training-time attacks against them are a named sector-level concern: healthcare-sector guidance identifies model poisoning and adversari...
Source: arXiv - Machine Learning | 10 hours ago
4. DualView: Preventing Indirect Prompt Injection in Personal AI Agents
arXiv:2607.03821v2 Announce Type: replace-cross Abstract: Personal AI agents that run on the user's local machine automate daily tasks including web search, email, and file management. Their access to computer resources, including the network, file system, and shell, exposes them to indirect pro...
Source: arXiv - AI | 10 hours ago
5. Evaluating LLM-Generated Rules for Heart Disease Prediction
arXiv:2609.13192v1 Announce Type: new Abstract: This study compares traditional machine learning models and Large Language Model (LLM)-generated rule-based systems for heart disease prediction using the UCI Heart Disease dataset. Several classifiers, including Logistic Regression, K-Nearest Neig...
Source: arXiv - Machine Learning | 10 hours ago
6. HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving
arXiv:2609.08306v3 Announce Type: replace-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 harveste...
Source: arXiv - Machine Learning | 10 hours ago
7. Admissable: Training Reinforcement Learning Agents against Adversarial Missingness
arXiv:2609.15297v1 Announce Type: new Abstract: In order to make Reinforcement Learning algorithms applicable in real world scenarios, safety must be ensured even under adverse operating conditions. In this work, we consider the challenge of adversarial feature missingness: a scenario in which a...
Source: arXiv - Machine Learning | 10 hours ago
8. Are Targeted Data Poisoning Attacks as Effective as We Think?
arXiv:2509.06896v3 Announce Type: replace Abstract: Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true worst-c...
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.