Here's your daily roundup of the most relevant AI and ML news for May 11, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs
arXiv:2605.06669v1 Announce Type: cross Abstract: Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that...
Source: arXiv - Machine Learning | 10 hours ago
2. MIPIAD: Multilingual Indirect Prompt Injection Attack Defense with Qwen -- TF-IDF Hybrid and Meta-Ensemble Learning
arXiv:2605.07269v1 Announce Type: cross Abstract: Indirect prompt injection remains a persistent weakness in retrieval-augmented and tool-using LLM systems, and the problem becomes harder to characterise in multilingual settings. We present MIPIAD, a defense framework evaluated on English and Ba...
Source: arXiv - Machine Learning | 10 hours ago
3. MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
arXiv:2605.07850v1 Announce Type: cross Abstract: With the rise in scale for deep learning models to billions of parameters, the computational cost of fine-tuning remains a significant barrier to deployment. While Low-Rank Adaptation (LoRA) has become the standard for parameter-efficient fine-tu...
Source: arXiv - Machine Learning | 10 hours ago
4. UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function
arXiv:2410.21438v3 Announce Type: replace-cross Abstract: By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequentially to the pretrained model. Because SFT and alignmen...
Source: arXiv - Machine Learning | 10 hours ago
5. Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs
arXiv:2605.07961v1 Announce Type: new Abstract: Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs). Built upon federated learning, FFT enables distributed agents to jointly refine a shared pretrained LLM by aggregati...
Source: arXiv - Machine Learning | 10 hours ago
6. Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics
arXiv:2605.06902v1 Announce Type: new Abstract: Adversarial robustness has been studied extensively for offline deep networks, but less is known about strict single-pass streaming neural learners. This paper studies adversarial robustness in Fuzzy ARTMAP, an Adaptive Resonance Theory architectur...
Source: arXiv - Machine Learning | 10 hours ago
7. Disagreement-Regularized Importance Sampling for Adversarial Label Corruption
arXiv:2605.07551v1 Announce Type: new Abstract: Standard Importance Sampling (IS) collapses under label corruption because high-norm examples, prioritized for variance reduction, are often adversarial outliers. We formalize this misalignment using an $\varepsilon$-contamination model and propose...
Source: arXiv - Machine Learning | 10 hours ago
8. Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents
arXiv:2605.07138v1 Announce Type: cross Abstract: Reinforcement learning from verifiable emotion rewards RLVER has produced language models with strong empathetic performance, evaluated on benchmarks that assume cooperative, honest users. Yet real emotional interactions systematically violate th...
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.