Here's your daily roundup of the most relevant AI and ML news for August 24, 2026. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting
arXiv:2608.20572v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) face a dual challenge: vulnerability to adversarial attacks and prohibitive training cost. Adversarial training is effective but expensive, a burden that grows as learning shifts to the energy-constrained edge. ...
Source: arXiv - Machine Learning | 10 hours ago
2. Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
arXiv:2608.17310v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and sparse rewards, exposing several limitations of RL: its heavyweight backpr...
Source: arXiv - Machine Learning | 10 hours ago
3. Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence
arXiv:2608.20820v1 Announce Type: new Abstract: Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context. Existing certified robustness methods are limited to single-turn inputs; naive multi-turn composition yields bounds that...
Source: arXiv - AI | 10 hours ago
4. When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space
arXiv:2607.15218v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded jailbreak is t...
Source: arXiv - AI | 10 hours ago
5. Fine-tuning an ECG Foundation Model to Predict Coronary CT Angiography Outcomes
arXiv:2512.05136v4 Announce Type: replace-cross Abstract: Coronary artery disease (CAD) remains a major global public health burden, yet scalable pre-imaging risk stratification tools are limited. In this multicenter study, we developed and validated an artificial intelligence-enabled electrocar...
Source: arXiv - AI | 10 hours ago
6. Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI
arXiv:2608.21172v1 Announce Type: new Abstract: Federated fine-tuning enables large language models to adapt on edge devices without centralizing private data, but practical deployments must address hardware instability and adversarial update corruption together. Thermally constrained clients ma...
Source: arXiv - Machine Learning | 10 hours ago
7. RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
arXiv:2605.01913v2 Announce Type: replace Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded in ...
Source: arXiv - Machine Learning | 10 hours ago
Industry News
8. OpenAI says California should strengthen its AI safety bill
OpenAI is calling for California to strengthen SB 53, an AI safety bill that the company previously opposed.
Source: TechCrunch - AI | 1 day 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.