Here's your daily roundup of the most relevant AI and ML news for August 25, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
arXiv:2601.16890v2 Announce Type: replace-cross Abstract: Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting noise or altering semantics, yet no existing framework exp...
Source: arXiv - Machine Learning | 10 hours ago
2. Localize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection Attack
arXiv:2605.25194v3 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balance efficiency and defense...
Source: arXiv - Machine Learning | 10 hours ago
3. Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness
arXiv:2608.10008v3 Announce Type: replace-cross Abstract: LLM recommenders for top-K item suggestion regularly emit titles outside the target catalog. Prior audits report a binary out-of-domain rate; none ask whether the model knew. We jointly audit hallucination rate (OOD@10) and verbalized-con...
Source: arXiv - Machine Learning | 10 hours ago
4. Adversarial Agents on Topology Optimization: Understanding the Fragility and Robustness of Deep Learning-based and Physics-Based Design Models under Adversarial Perturbation
arXiv:2608.22606v1 Announce Type: new Abstract: Topology optimization, using both physic-based approaches and deep learning surrogates, serves as a cornerstone for generative design agents in cyber-manufacturing systems. While deep learning surrogates have gained widespread adoption due to their...
Source: arXiv - Machine Learning | 10 hours ago
5. A New Type of Adversarial Examples
arXiv:2510.19347v2 Announce Type: replace Abstract: Most machine learning models are vulnerable to adversarial examples, which poses security concerns on these models. Adversarial examples are crafted by applying subtle but intentionally worst-case modifications to examples from the dataset, lea...
Source: arXiv - Machine Learning | 10 hours ago
6. Breaking the Assumptions: Auditing Input-Side Jailbreak Defenses Against Semantic Attacks
arXiv:2608.21895v1 Announce Type: cross Abstract: Locally deployed Large Language Models (LLMs) via inference engines such as Ollama run without the moderation and abuse detection present in API-served models. Therefore, the safety of LLMs depends on the defense mechanisms used, and their effect...
Source: arXiv - AI | 10 hours ago
7. Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classification
arXiv:2507.13727v2 Announce Type: replace Abstract: Adversarial training is a promising strategy for enhancing robustness against adversarial attacks, but its impact on generalization under substantial distribution shifts in audio classification remains largely unexplored. We address this gap by...
Source: arXiv - Machine Learning | 10 hours ago
8. Continuous Adversarial MeanFlow Transfer
arXiv:2608.19540v2 Announce Type: replace Abstract: Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves its costly multi-step sampling unaddressed, and existing acceleration met...
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.