Here's your daily roundup of the most relevant AI and ML news for June 12, 2026. We're also covering 8 research developments. Click through to read the full articles from our curated sources.
Research & Papers
1. MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling
arXiv:2606.12935v1 Announce Type: new Abstract: Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, incurring substantial computational overhead. We observe that probing partial traces at int...
Source: arXiv - AI | 10 hours ago
2. Learning to Inject: Automated Prompt Injection via Reinforcement Learning
arXiv:2602.05746v2 Announce Type: replace Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still rely on human red-teamers and hand-crafted prompts. Adapting automated jailbreak optimizers does not close this gap: jailbreaks shape models toward gene...
Source: arXiv - Machine Learning | 10 hours ago
3. Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
arXiv:2606.11409v1 Announce Type: new Abstract: Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly. In practice, the computational expense of different attack s...
Source: arXiv - Machine Learning | 10 hours ago
4. Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks
arXiv:2606.11615v1 Announce Type: cross Abstract: The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent. To address this challenge, we propose Adv-TGD, a generative adversarial attack framework that synthesi...
Source: arXiv - Machine Learning | 10 hours ago
5. MobileFineTuner: A Mobile-Native Framework for On-Device LLM Fine-Tuning in Real-World Embedded AI Applications
arXiv:2512.08211v2 Announce Type: replace Abstract: Large language models (LLMs) are moving from cloud-centric services toward on-device embedded AI, where models interact with private, longitudinal signals sensed from users and their physical environments. Mobile phones are a natural platform f...
Source: arXiv - Machine Learning | 10 hours ago
6. Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization
arXiv:2606.12251v1 Announce Type: new Abstract: Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations. To address this, we investigate whether reinforcement learning (RL) ...
Source: arXiv - Machine Learning | 10 hours ago
7. Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization
arXiv:2606.11804v1 Announce Type: cross Abstract: Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data summarization determines which information is retained and passed to subsequent learning or decision modules....
Source: arXiv - Machine Learning | 10 hours ago
8. Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
arXiv:2605.31219v2 Announce Type: replace-cross Abstract: While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wise attacks frequently introduce unnatural, high-frequency visual artifacts, while late...
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.