Here's your daily roundup of the most relevant AI and ML news for September 22, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents
arXiv:2609.22510v1 Announce Type: cross Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI), where adversarial instructions are embedded in retrieved content. Conventional IPIs fire on contact: the moment an agent ingests ...
Source: arXiv - Machine Learning | 10 hours ago
2. Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision
arXiv:2609.24249v1 Announce Type: new Abstract: Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small perturbations, almost imperceptible to humans, which significantly alter the model's prediction. These a...
Source: arXiv - Machine Learning | 10 hours ago
3. Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing
arXiv:2607.12500v2 Announce Type: replace Abstract: Deep learning models for online handwriting recognition have been shown effective and are increasingly deployed in practical applications. However, their vulnerability to adversarial attacks is still a challenge. Existing adversarial methods ar...
Source: arXiv - Machine Learning | 10 hours ago
4. HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference
arXiv:2609.21484v1 Announce Type: cross Abstract: Homomorphic encryption (HE) has emerged as a promising approach to privacy-preserving machine learning (PPML), enabling computation directly over encrypted data. In HE-based PPML, a client submits an encrypted input to the server, which evaluates...
Source: arXiv - AI | 10 hours ago
5. Taming the Adversary: A Cost-to-Disturbance Ratio Approach to Adversarial Reinforcement Learning
arXiv:2603.12110v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) policies trained in simulation often degrade once deployed on real systems, where the controller must reject external disturbances that were never encountered in simulation. Robust RL addresses this by exposing...
Source: arXiv - AI | 10 hours ago
6. Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport
arXiv:2609.22240v1 Announce Type: new Abstract: The purpose of this paper is to rigorously quantify the statistical and learning-theoretic properties of adversarial training models for classification. Equivalently, we establish the statistical properties of empirical optimal partial transport. P...
Source: arXiv - Machine Learning | 10 hours ago
7. Robust Market Making with Hawkes Order Flow and Price Impact via Adversarial Reinforcement Learning
arXiv:2609.22785v1 Announce Type: new Abstract: Market-making strategies in real limit order book markets face substantial model uncertainty and regime-shift risk. Existing adversarial reinforcement learning approaches improve robustness by formulating the Avellaneda--Stoikov market-making probl...
Source: arXiv - Machine Learning | 10 hours ago
8. The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits
arXiv:2609.23092v1 Announce Type: new Abstract: Adversarial multi-objective bandits hold the potential to help us optimize choices (arms) whose reward is a multidimensional vector chosen by an adversary and whose performance is measured by Pareto regret. We define loss as one minus reward and me...
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.