Here's your daily roundup of the most relevant AI and ML news for August 27, 2026. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning
arXiv:2608.25133v1 Announce Type: new Abstract: The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machine learning models. However, the involvement of a large number of users in FL also creates open o...
Source: arXiv - Machine Learning | 10 hours ago
2. FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment
arXiv:2608.24551v1 Announce Type: cross 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 a...
Source: arXiv - AI | 10 hours ago
3. '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
4. Adversarial Training of Linear Models under Stealthy Attacks
arXiv:2608.25681v1 Announce Type: new Abstract: Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and adversarial training have been proposed, but such approaches lack guarantees against stealthy attacks. We t...
Source: arXiv - Machine Learning | 10 hours ago
5. Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity
arXiv:2608.26043v1 Announce Type: new Abstract: Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives within a single parameter configuration, leading to ...
Source: arXiv - Machine Learning | 10 hours ago
6. Continuous Adversarial Flow Models
arXiv:2604.11521v2 Announce Type: replace Abstract: We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-error criterion, our approach introduces a learned discriminator to...
Source: arXiv - Machine Learning | 10 hours ago
7. Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors
arXiv:2608.23873v1 Announce Type: new 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 a...
Source: arXiv - AI | 10 hours ago
Tech & Development
8. Shieldprompt – test your LLM against prompt injection – no dependencies
Article URL: https://github.com/Jograph17/shieldprompt Comments URL: https://news.ycombinator.com/item?id=49464312 Points: 3
Comments: 0
Source: Hacker News - AI | just now
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.