Here's your daily roundup of the most relevant AI and ML news for August 17, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack
arXiv:2605.25194v2 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
2. Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty
arXiv:2608.13651v1 Announce Type: cross Abstract: We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system $x_{t+1} = ax_t + u_t + w_t$, $x_0=0$, $|w|_\infty \le 1$, where the constant pole $a \in [-\Delta, \Delta]$ is unknown in s...
Source: arXiv - Machine Learning | 10 hours ago
3. A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation
arXiv:2608.14329v1 Announce Type: cross Abstract: Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute. Our position is that any ...
Source: arXiv - Machine Learning | 10 hours ago
4. Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
arXiv:2608.13574v1 Announce Type: new Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols. These capabilities make agents useful, but they also introduce risks related to over-privileged...
Source: arXiv - AI | 10 hours ago
5. The Architect: Interactive Visualization of Deep Learning Mathematics Directly in Microsoft Excel
arXiv:2608.13572v1 Announce Type: cross Abstract: We present The Architect, a system that turns Microsoft Excel into an interactive view of deep learning mathematics. A user describes a neural network in a compact table. The system then generates a workbook that shows the full forward pass and, ...
Source: arXiv - AI | 10 hours ago
6. P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
arXiv:2608.14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on personal devices. Cloud-bound requests must exclude personally identifiable information (PII) to pr...
Source: arXiv - AI | 10 hours ago
7. Adversarial Learning of Classifier-Free Guidance Schedules
arXiv:2608.14038v1 Announce Type: new Abstract: Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically applies a static, global scale across all timesteps, samples, and conditions -- a choice that is ...
Source: arXiv - Machine Learning | 10 hours ago
8. Language-Specific Gaps in AI Safety Training Datasets
arXiv:2608.13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking users. We show that these collection-level coverage claims frequently ...
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.