Here's your daily roundup of the most relevant AI and ML news for June 23, 2026. Today's digest includes 2 security-focused stories. We're also covering 6 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. ShapedPlugin WordPress Pro Plugins Backdoored in Supply Chain Attack
Multiple WordPress plugins from ShapedPlugin were compromised in a supply chain attack after unknown threat actors managed to tamper with the official release channels and push backdoor code.
"Attackers compromised the vendor's build and distribution pipeline, injecting backdoor code into Pro pl...
Source: The Hacker News (Security) | 20 hours ago
2. OpenAI Expands Daybreak With GPT-5.5-Cyber to Help Defenders Patch Security Flaws
OpenAI on Monday said it's releasing an improved version of its GPT‑5.5‑Cyber model to trusted defenders as part of the Daybreak initiative the artificial intelligence (AI) company announced last month.
Calling GPT‑5.5‑Cyber its "strongest model yet for finding and helping patch software vu...
Source: The Hacker News (Security) | 10 hours ago
Research & Papers
3. Stealthy World Model Manipulation via Data Poisoning
arXiv:2606.18697v2 Announce Type: replace Abstract: Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of updating world models from collected experience creates a training-time attack surface: adversar...
Source: arXiv - Machine Learning | 10 hours ago
4. Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks
arXiv:2606.20893v1 Announce Type: cross Abstract: Deep learning-based audio classification systems, including automatic speaker verification, are vulnerable to adversarial attacks. Realistic real-time threat assessment remains difficult because optimization-based methods, such as projected gradi...
Source: arXiv - AI | 10 hours ago
5. EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
arXiv:2606.23038v1 Announce Type: new Abstract: Rubric-based rewards offer interpretable and fine-grained optimization signals for reinforcement learning in open-ended tasks where verifiable answers are unavailable. However, pre-constructed rubrics remain static throughout training, creating a f...
Source: arXiv - Machine Learning | 10 hours ago
6. Robustness Cannot be Reduced to Regularization: Studying Adversarial Training Beyond the Linear Case
arXiv:2606.21488v1 Announce Type: new Abstract: The vulnerability of ML models to adversarial examples has recently emerged as a major concern. While adversarial training is one of the most effective countermeasures to this issue, its high computational cost remains an obstacle to practical depl...
Source: arXiv - Machine Learning | 10 hours ago
7. Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
arXiv:2606.22056v1 Announce Type: new Abstract: Adversarial imitation learning (AIL) achieves high-quality imitation compared to behavioral cloning (BC), but demands substantial online environment interaction. Recent empirical work has explored initializing AIL algorithms with BC pretrained poli...
Source: arXiv - Machine Learning | 10 hours ago
8. When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents
arXiv:2606.22864v1 Announce Type: new Abstract: Hidden-state probing -- a linear classifier on a frozen vision-language model's internal activations -- has emerged as an attractive evaluation tool for flagging indirect prompt injection (IPI) in multimodal computer-use agents before the agent emi...
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.