Here's your daily roundup of the most relevant AI and ML news for July 03, 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. Critical Cursor Flaws Could Let Prompt Injection Escape Sandbox and Run Commands
Two flaws in Cursor, an AI code editor, could let a single, ordinary-looking prompt break out of the editor's safety sandbox and run any command on a developer's computer. There is no click to fall for and no approval box to ignore.
Cato AI Labs found the pair and named them DuneSlide. They...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
2. Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
arXiv:2607.01278v1 Announce Type: new Abstract: The research proposes a multilayer Q-matrix-embedded neural network for cognitive diagnosis (M-QCDNet), which integrates the structural interpretability of cognitive diagnostic models (CDMs) with the deep learning neural network (NN). M-QCDNet stru...
Source: arXiv - Machine Learning | 10 hours ago
3. kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
arXiv:2607.02072v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominately rely on fine-tuning to build classifiers, which often suffer from low gene...
Source: arXiv - Machine Learning | 10 hours ago
4. Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers
arXiv:2607.01679v1 Announce Type: cross Abstract: Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security analysts rely on to understand and triage alerts. We extend our prior MLP conference study to R...
Source: arXiv - Machine Learning | 10 hours ago
5. From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection
arXiv:2512.10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored. Recent work suggests that both graph neural network (GNN)-based and...
Source: arXiv - Machine Learning | 10 hours ago
6. Black-Box Inference of LLM Architectural Properties with Restrictive API Access
arXiv:2607.01313v1 Announce Type: new Abstract: In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures. However, prior work has shown that given limited API access to an LLM (namely, top-$k$ logits and/or a logit bias function), one can recover...
Source: arXiv - Machine Learning | 10 hours ago
7. Q-GAIN: A Python Package for Machine Learning and Physically Informed Analysis Applications
arXiv:2607.02413v1 Announce Type: cross Abstract: Here we describe the quantum gas analysis and inference (Q-GAIN) Python package, which enables rapid deployment of machine learning (ML) and physics-informed analysis techniques for cold-atom experiments. Out of the box, Q-GAIN implements classif...
Source: arXiv - Machine Learning | 10 hours ago
8. Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
arXiv:2607.01918v1 Announce Type: new Abstract: We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-shot forecasting bu...
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.