Here's your daily roundup of the most relevant AI and ML news for August 28, 2026. Today's digest includes 1 security-focused story. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate data exfiltration via prompt injection and Kiro Powers.
The security flaw, which does not have a CV...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
2. Adversarial Training Without Input Gradients via Low-Rank Householder Expansions
arXiv:2608.26963v1 Announce Type: new Abstract: This work concerns adversarial training against the small-norm adversarial examples that arise from the inherent input instability of a trained deep neural network. Examples in this class are small as measured in the relative $\ell^2$-norm, and the...
Source: arXiv - Machine Learning | 10 hours ago
3. Federated Adversarial Training with Transformers
arXiv:2206.02131v2 Announce Type: replace Abstract: Federated learning (FL) has emerged to enable global model training over distributed clients' data while preserving its privacy. However, the global trained model is vulnerable to the evasion attacks especially, the adversarial examples (AEs), ...
Source: arXiv - Machine Learning | 10 hours ago
4. AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air
arXiv:2507.11515v2 Announce Type: replace Abstract: Operating Large Language Models (LLMs) on edge devices is increasingly challenged by limited communication bandwidth and strained computational and memory costs. Thus, cloud-assisted remote fine-tuning becomes indispensable. Nevertheless, exist...
Source: arXiv - Machine Learning | 10 hours ago
5. Fine-Tuning of Transformer models with Frames
arXiv:2608.26430v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) strategies such as Low-Rank Adaptation (LoRA) are effective solutions for fine-tuning large-scale pre-trained models; however, their memory requirements scale with the size of the model, $\mathcal{O}(dr)$, whe...
Source: arXiv - AI | 10 hours ago
6. Distinct Profiles of Run-to-Run Score Reliability and Expert-Panel Alignment Across Four LLM Evaluators of Simulated Japanese-Language AI-to-AI Counseling
arXiv:2507.02950v4 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly evaluate generated dialogue, but repeatable scores do not necessarily align with professional judgment. This observational fixed-benchmark study compared four configured LLM evaluator systems (GPT...
Source: arXiv - AI | 10 hours ago
7. Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners
arXiv:2608.27424v1 Announce Type: cross Abstract: Static scanners are increasingly used to identify executable or otherwise unsafe content in machine- learning artifacts, yet conventional evaluation metrics characterize only cases where a scanner yields a usable security judgment. We evaluate Mo...
Source: arXiv - AI | 10 hours ago
8. Stack Trace-Based Crash Deduplication with Transformer Adaptation
arXiv:2508.19449v2 Announce Type: replace-cross Abstract: Automated crash reporting systems generate large volumes of duplicate reports, overwhelming issue-tracking systems and increasing developer workload. Traditional stack trace-based deduplication methods---relying on string similarity, rule...
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.