Here's your daily roundup of the most relevant AI and ML news for July 17, 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. OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely.
"GPT‑Red is a strong red-teamer, and our previous models are highly vulnerable to its prompt injec...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
2. Adversarial Prompting Framework for AI Safety Assessment
arXiv:2607.13453v1 Announce Type: cross Abstract: Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actor...
Source: arXiv - AI | 10 hours ago
3. Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
arXiv:2607.14921v1 Announce Type: new Abstract: Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable deployment of these models. In recent years, some powerful adversarial example attacks have been proposed f...
Source: arXiv - Machine Learning | 10 hours ago
4. Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their defenses against cyberattacks. Last week the company released the latest version of its flagship LLM, GPT-5.6. OpenAI says that training it against GPT-Red made the model it...
Source: MIT Technology Review - AI | 1 day ago
5. GeoDetect: Geometric Adversarial Detection for VLPs
arXiv:2607.14737v1 Announce Type: cross Abstract: Vision-language pre-trained models (VLPs) are widely used in real-world applications. However, they remain vulnerable to adversarial attacks. Although adversarial detection methods have demonstrated success in single-modality settings (either vis...
Source: arXiv - Machine Learning | 10 hours ago
6. ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotion
arXiv:2607.03454v2 Announce Type: replace-cross Abstract: In this paper, we propose Adversarial Dynamics Priors (ADP) for perturbation-resilient humanoid locomotion control. Existing motion prior-based methods induce natural motion styles by imitating kinematic motion features, but they do not d...
Source: arXiv - Machine Learning | 10 hours ago
7. Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion
arXiv:2607.14371v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized AI services, but a critical tension emerges: while personalization improves model performance, it consumes scarce computational resources that users must share. When should a user invest in expensive...
Source: arXiv - Machine Learning | 10 hours ago
8. EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
arXiv:2606.30219v2 Announce Type: replace-cross Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify. This paper...
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.