Here's your daily roundup of the most relevant AI and ML news for August 26, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment
arXiv:2608.24551v1 Announce Type: new Abstract: Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate because financial tabular data involve domain-specific constraints, severe class imbalance, and asy...
Source: arXiv - Machine Learning | 10 hours ago
2. 'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
arXiv:2608.24191v1 Announce Type: cross Abstract: Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine years of WOAH proceedings. To investigate whether this absence has measurable consequences for c...
Source: arXiv - AI | 10 hours ago
3. Conditional GraphGANFed: Optimizing Graph-Structured Molecule Generation in Federated Generative Adversarial Networks
arXiv:2608.24610v1 Announce Type: new Abstract: Generative adversarial networks (GANs) have garnered considerable attention in molecular discovery for their ability to generate novel and high-quality molecules. To efficiently train a GAN model while preserving data privacy, GraphGANFed has been ...
Source: arXiv - Machine Learning | 10 hours ago
4. Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors
arXiv:2608.23873v1 Announce Type: cross Abstract: Everything a language model sees is tokens. The serving stack knows what each span is -- user input, tool output, instructions -- but the model must keep track of that itself, and it can lose track or be confused: text can be written to read like...
Source: arXiv - Machine Learning | 10 hours ago
5. An Efficient Minimax-Optimal Algorithm for Adversarial $m$-Set Bandits
arXiv:2608.12231v2 Announce Type: replace Abstract: We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items. The resulting action set contains $K=\binom{d}{m}$ element...
Source: arXiv - Machine Learning | 10 hours ago
6. MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs
arXiv:2602.06268v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, prompt injection attacks can steer these systems toward clinically unsafe or misleading outputs. W...
Source: arXiv - Machine Learning | 10 hours ago
7. NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
arXiv:2608.23959v1 Announce Type: cross Abstract: Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of attacks. Jailbreak attacks bypass safety mechanisms through crafted prompts, while neuron-level attacks directly prune safety-critical neurons post-dep...
Source: arXiv - Machine Learning | 10 hours ago
8. WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents
arXiv:2608.24017v1 Announce Type: cross Abstract: The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent execution into a browser security model centered on the Same-Origin Policy (SOP) leaves insuffic...
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.