Here's your daily roundup of the most relevant AI and ML news for July 21, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Geometric origin of adversarial vulnerability in deep learning
arXiv:2509.01235v2 Announce Type: replace Abstract: Balancing training accuracy and adversarial robustness has beeen a challenge since the birth of deep learning. Here, we introduce a geometry-aware deep learning framework that leverages layer-wise local training to sculpt the internal represent...
Source: arXiv - Machine Learning | 10 hours ago
2. PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection
arXiv:2607.16199v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on a Planner to decompose goals into sub-task sequences that downstream Executor and Critic agents execute and audit. We identify the planning phase as a critical attack surface: a single injection into the...
Source: arXiv - AI | 10 hours ago
3. Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models
arXiv:2607.17779v1 Announce Type: new Abstract: Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly in generating Not-Safe-For-Work (NSFW) images. Most existing jailbre...
Source: arXiv - AI | 10 hours ago
4. How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
arXiv:2605.06605v4 Announce Type: replace Abstract: Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.g., jailbreaks or successful task completion by an agent -- often emerge ...
Source: arXiv - Machine Learning | 10 hours ago
5. A Multi-Model Hybrid Defense Approach Against White-box Adversarial Attacks in Computer Network Traffic
arXiv:2607.17105v1 Announce Type: cross Abstract: It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System (NIDS). However, ...
Source: arXiv - Machine Learning | 10 hours ago
6. Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
arXiv:2603.22590v2 Announce Type: replace Abstract: With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become highly relevant. We observe that changing the precision of an ASR model during inferenc...
Source: arXiv - Machine Learning | 10 hours ago
7. KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?
arXiv:2607.16241v1 Announce Type: new Abstract: Recent large language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on benchmarks such as KernelBench. Building upon this foundational framework, we demonstrate that frontier models frequently engage in reward hac...
Source: arXiv - Machine Learning | 10 hours ago
8. ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning
arXiv:2607.16323v1 Announce Type: cross Abstract: Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardiography (ECHO) or cardiac magnetic resonance (CMR). Furthermore, mo...
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.