Here's your daily roundup of the most relevant AI and ML news for April 21, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
arXiv:2604.16586v1 Announce Type: new Abstract: Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and biological behavior. This survey traces four complementary paradigms, including Quantum, Descript...
Source: arXiv - Machine Learning | 10 hours ago
2. InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control
arXiv:2604.15373v1 Announce Type: cross Abstract: We propose InfoChess, a symmetric adversarial game that elevates competitive information acquisition to the primary objective. There is no piece capture, removing material incentives that would otherwise confound the role of information. Instead,...
Source: arXiv - AI | 10 hours ago
3. Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing
arXiv:2604.15725v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have demonstrated strong capabilities in generating step-by-step reasoning chains alongside final answers, enabling their deployment in high-stakes domains such as healthcare and education. While prior jailbreak atta...
Source: arXiv - AI | 10 hours ago
4. Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover
arXiv:2603.11331v2 Announce Type: replace-cross Abstract: Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that strong adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth obse...
Source: arXiv - AI | 10 hours ago
5. Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations
arXiv:2604.16515v1 Announce Type: cross Abstract: The rapid proliferation of Multimodal Large Language Models (MLLMs) has enabled mobile agents to execute high-stakes financial transactions, but their adversarial robustness remains underexplored. We identify Visual Dominance Hallucination (VDH),...
Source: arXiv - Machine Learning | 10 hours ago
6. Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition
arXiv:2604.17803v1 Announce Type: cross Abstract: Post-training Large Language Models requires diverse, high-quality data which is rare and costly to obtain, especially in low resource domains and for multi-turn conversations. Common solutions are crowdsourcing or synthetic generation, but both ...
Source: arXiv - Machine Learning | 10 hours ago
7. Duality for the Adversarial Total Variation
arXiv:2604.18540v1 Announce Type: cross Abstract: Adversarial training of binary classifiers can be reformulated as regularized risk minimization involving a nonlocal total variation. Building on this perspective, we establish a characterization of the subdifferential of this total variation usi...
Source: arXiv - Machine Learning | 10 hours ago
8. Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
arXiv:2512.12069v3 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both generalizable to novel threats and efficient for practical deployment. Many current strategies fa...
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.