Here's your daily roundup of the most relevant AI and ML news for March 25, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
arXiv:2511.05919v3 Announce Type: replace-cross Abstract: LLMs are now an integral part of information retrieval. As such, their role as question answering chatbots raises significant concerns due to their shown vulnerability to adversarial man-in-the-middle (MitM) attacks. Here, we propose the ...
Source: arXiv - AI | 10 hours ago
2. Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning
arXiv:2410.12164v2 Announce Type: replace-cross Abstract: Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks (e.g., NL-to-Code and data cleaning) remains suboptimal. Improving performance typically r...
Source: arXiv - Machine Learning | 10 hours ago
3. Metaphor-based Jailbreak Attacks on Text-to-Image Models
arXiv:2512.10766v2 Announce Type: replace-cross Abstract: Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and indu...
Source: arXiv - AI | 10 hours ago
4. Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression
arXiv:2512.09275v2 Announce Type: replace-cross Abstract: Positional encoding (PE) is a core architectural component of Transformers, yet its impact on the Transformer's generalization and robustness remains unclear. In this work, we provide the first generalization analysis for a single-layer T...
Source: arXiv - Machine Learning | 10 hours ago
5. Targeted Adversarial Traffic Generation : Black-box Approach to Evade Intrusion Detection Systems in IoT Networks
arXiv:2603.23438v1 Announce Type: cross Abstract: The integration of machine learning (ML) algorithms into Internet of Things (IoT) applications has introduced significant advantages alongside vulnerabilities to adversarial attacks, especially within IoT-based intrusion detection systems (IDS). ...
Source: arXiv - AI | 10 hours ago
6. Adversarial Vulnerabilities in Neural Operator Digital Twins: Gradient-Free Attacks on Nuclear Thermal-Hydraulic Surrogates
arXiv:2603.22525v1 Announce Type: new Abstract: Operator learning models are rapidly emerging as the predictive core of digital twins for nuclear and energy systems, promising real-time field reconstruction from sparse sensor measurements. Yet their robustness to adversarial perturbations remain...
Source: arXiv - Machine Learning | 10 hours ago
7. Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
arXiv:2603.22590v1 Announce Type: new Abstract: With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become critical. We observe that changing the precision of an ASR model during inference reduces t...
Source: arXiv - Machine Learning | 10 hours ago
8. Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Role of Bellman Constraints
arXiv:2603.22713v1 Announce Type: new Abstract: Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors in behavioral cloning (BC), but often exhibits training instability due to adversarial optimization. To avoid this issue, a class of non-adversari...
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.