Here's your daily roundup of the most relevant AI and ML news for July 31, 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. Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations
Anthropic on Thursday became the latest artificial intelligence (AI) company to reveal that three of its models, including Claude Opus 4.7, Mythos 5, and an unnamed research model, had breached three unnamed organizations during cybersecurity testing without its knowledge.
The AI firm said the e...
Source: The Hacker News (Security) | 7 hours ago
Research & Papers
2. Towards an Automated Test of LLM Security Knowledge
arXiv:2607.18496v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks. Consequently, LLM performance on security tasks is an active area of measurement and research, often with a focus on i...
Source: arXiv - AI | 10 hours ago
3. Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control
arXiv:2607.01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agen...
Source: arXiv - AI | 10 hours ago
4. Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers
arXiv:2607.27737v1 Announce Type: new Abstract: Deep neural networks (DNNs) have achieved remarkable success in classical machine learning problems. However, they are known to be vulnerable to adversarial attacks. Countermeasures proposed in the literature, notably Information Bottleneck Distill...
Source: arXiv - Machine Learning | 10 hours ago
5. ZAPs: A Reward Attribution Framework for DeFi Ecosystems with Adversarial-Robust Scoring via Parallel Anomaly Ensemble Detection
arXiv:2607.27859v1 Announce Type: cross Abstract: Incentive programs are central to user acquisition in decentralized finance, but many reward systems rely on raw volume, transaction count, and wallet count, making them vulnerable to bots and sybil operations. We present ZAPs, a reward attributi...
Source: arXiv - Machine Learning | 10 hours ago
6. Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators
arXiv:2607.27995v1 Announce Type: cross Abstract: Adversarial training has emerged as a powerful approach for protecting models against adversarial attacks in a broad range of real-world applications. In this paper, we study adversarial training in the reproducing kernel Hilbert space (RKHS) fra...
Source: arXiv - Machine Learning | 10 hours ago
7. GPT-Red: Automated Red Teaming via Self-Play at Scale
arXiv:2607.26115v1 Announce Type: cross Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluate and improve the robustness of our production systems. To this en...
Source: arXiv - AI | 10 hours ago
8. HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data
arXiv:2607.27635v1 Announce Type: cross Abstract: Wearable sensors continuously capture fine-grained multivariate time-series data, providing opportunities to model behavioural patterns associated with health outcomes. However, existing deep learning methods prioritise predictive accuracy over i...
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.