Here's your daily roundup of the most relevant AI and ML news for March 23, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
arXiv:2603.19562v1 Announce Type: new Abstract: Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems, each addressed with modality-specific patches. This study first reveals that they share a common geometric origin: the in...
Source: arXiv - Machine Learning | 10 hours ago
2. A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2
arXiv:2603.19253v1 Announce Type: cross Abstract: Argument mining (AM) is an interdisciplinary research field focused on the automatic identification and classification of argumentative components, such as claims and premises, and the relationships between them. Recent advances in large language...
Source: arXiv - AI | 10 hours ago
3. Cross-site scripting adversarial attacks based on deep reinforcement learning: Evaluation and extension study
arXiv:2502.19095v2 Announce Type: replace-cross Abstract: Cross-site scripting (XSS) poses a significant threat to web application security. While Deep Learning (DL) has shown remarkable success in detecting XSS attacks, it remains vulnerable to adversarial attacks due to the discontinuous natur...
Source: arXiv - AI | 10 hours ago
4. A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness
arXiv:2601.03273v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greate...
Source: arXiv - AI | 10 hours ago
5. Prompt Injection as Role Confusion
arXiv:2603.12277v2 Announce Type: replace-cross Abstract: Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models infer roles from how text is written, not where it comes from. We design novel role probes to...
Source: arXiv - AI | 10 hours ago
6. Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences
arXiv:2603.20025v1 Announce Type: cross Abstract: We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,\Gamma)$-divergences, we prove a new infimal subadditivity principle showing that, under sui...
Source: arXiv - Machine Learning | 10 hours ago
7. KoALA: KL-L0 Adversarial Detector via Label Agreement
arXiv:2510.12752v2 Announce Type: replace Abstract: Deep neural networks are highly susceptible to adversarial attacks, which pose significant risks to security- and safety-critical applications. We present KoALA (KL-L0 Adversarial detection via Label Agreement), a novel, semantics-free adversar...
Source: arXiv - Machine Learning | 10 hours ago
8. Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives
arXiv:2603.18972v2 Announce Type: replace Abstract: Multi-dueling bandits, where a learner selects $m \geq 2$ arms per round and observes only the winner, arise naturally in many applications including ranking and recommendation systems, yet a fundamental question has remained open: can a single...
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.