Here's your daily roundup of the most relevant AI and ML news for July 14, 2026. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents
arXiv:2605.01143v2 Announce Type: replace Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions can ma...
Source: arXiv - AI | 10 hours ago
2. IG-GAN: A Generative Adversarial Network for Aerodynamic Data Generation Based on Intrinsic Geometry
arXiv:2607.11497v1 Announce Type: new Abstract: Existing generative models learn data distributions in flat Euclidean space. However, most data in our real world are manifolds embedded in high dimensional Euclidean space. Therefore, we propose an intrinsic-geometry-based generative adversarial n...
Source: arXiv - Machine Learning | 10 hours ago
3. Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information
arXiv:2607.09993v1 Announce Type: cross Abstract: Adversarial team games (ATGs) with asymmetric information, such as adversarial path-finding, goal search, and reachability games on graphs, require strategies that are robust to hidden opponent types, such as a hidden goal flag, and to deception....
Source: arXiv - Machine Learning | 10 hours ago
4. Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints
arXiv:2509.20114v3 Announce Type: replace Abstract: We study \emph{online episodic Constrained Markov Decision Processes} (CMDPs) under both stochastic and adversarial constraints. We provide a novel algorithm whose guarantees greatly improve those of the state-of-the-art best-of-both-worlds alg...
Source: arXiv - Machine Learning | 10 hours ago
5. Enhancing Adversarial Transferability through Block Stretch and Shrink
arXiv:2511.17688v2 Announce Type: replace Abstract: Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs. Existing analyses mainly explain their efficacy from image diversity, semantic preservation, attention variance or hypothes...
Source: arXiv - Machine Learning | 10 hours ago
6. AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation
arXiv:2607.11063v1 Announce Type: new Abstract: Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances. Most existing methods rely on white-box access to target model gradients, which is often unrealistic for real-world deploy...
Source: arXiv - AI | 10 hours ago
7. NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations
arXiv:2607.10490v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages can carry indirect prompt injections. We present NetInjectBench, a 130-scenario benchmark that separates...
Source: arXiv - Machine Learning | 10 hours ago
Tech & Development
8. Show HN: Libargus:Low-latency local LLM runner via OpenJDK Panama FFM (Java 22)
Most existing approaches for running local LLM inference within the JVM ecosystem rely on spawning out-of-process daemons via REST sidecars (introducing major serialization and IPC overhead) or loading monolithic JNI wrappers that introduce object-copying overhead and heavy Garbage Collection pre...
Source: Hacker News - AI | just now
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.