Here's your daily roundup of the most relevant AI and ML news for May 19, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
arXiv:2604.27019v2 Announce Type: replace Abstract: Safety-aligned language models must refuse harmful requests without collapsing into broad over-refusal, yet it remains unclear how dynamic adversarial fine-tuning changes the internal carriers of refusal. We study one 7B backbone under supervis...
Source: arXiv - Machine Learning | 10 hours ago
2. Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
arXiv:2605.16205v1 Announce Type: new Abstract: Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed across components. Yet practitio...
Source: arXiv - AI | 10 hours ago
3. A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
arXiv:2605.18666v1 Announce Type: new Abstract: Gradient-based adversarial attacks subtly manipulate inputs of Machine Learning (ML) models to induce incorrect predictions. This paper investigates whether careful architectural choices alone can yield an inherently robust Deep Neural Network (DNN...
Source: arXiv - Machine Learning | 10 hours ago
4. When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making
arXiv:2602.04003v3 Announce Type: replace Abstract: Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and act ...
Source: arXiv - AI | 10 hours ago
5. Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings
arXiv:2605.16993v1 Announce Type: cross Abstract: Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions that do not reflect the realities of healthcare delivery in low-resource settings. This study prese...
Source: arXiv - Machine Learning | 10 hours ago
6. Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training
arXiv:2505.02360v2 Announce Type: replace Abstract: Adversarial training is a cornerstone of robust deep learning, but fast methods like the Fast Gradient Sign Method (FGSM) often suffer from Catastrophic Overfitting (CO), where models become robust to single-step attacks but fail against multi-...
Source: arXiv - Machine Learning | 10 hours ago
7. Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
arXiv:2510.10140v2 Announce Type: replace Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of downstream applications, including tropical cyclone (TC) prediction. In this paper, we investigate...
Source: arXiv - Machine Learning | 10 hours ago
8. Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
arXiv:2605.15394v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstractions when trained to predict latent representations rather than observed outputs. For autoregressive language-model fine-tuning the principle e...
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.