Here's your daily roundup of the most relevant AI and ML news for September 11, 2026. Today's digest includes 1 security-focused story. We're also covering 7 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic on Wednesday disclosed a fourth incident in which its artificial intelligence (AI) model broke into real third-party systems, marking the latest in a growing list of cases that have raised concerns about the security risks posed by autonomous AI agents.
The AI company said the incident...
Source: The Hacker News (Security) | 1 day ago
Research & Papers
2. DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents
arXiv:2609.10892v1 Announce Type: cross Abstract: When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs thre...
Source: arXiv - Machine Learning | 10 hours ago
3. Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning
arXiv:2609.09553v1 Announce Type: cross Abstract: Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypasses that allow an adversarial user to elicit unwanted or harmful outputs from models. Arbitrary ...
Source: arXiv - AI | 10 hours ago
4. Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
arXiv:2609.10142v1 Announce Type: cross Abstract: Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors during fine-tuning and removes them at evaluation...
Source: arXiv - AI | 10 hours ago
5. 'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
arXiv:2608.24191v2 Announce Type: replace-cross Abstract: Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine years of WOAH proceedings. To investigate whether this absence has measurable consequenc...
Source: arXiv - AI | 10 hours ago
6. Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations
arXiv:2609.10866v1 Announce Type: new Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications. Certification methods can improve robustness against adv...
Source: arXiv - Machine Learning | 10 hours ago
7. Empirical Evaluation of Data Poisoning Attacks in Supervised Learning
arXiv:2609.10952v1 Announce Type: cross Abstract: Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST with three baselin...
Source: arXiv - Machine Learning | 10 hours ago
8. What Makes Adversarial Examples Transfer Across Deepfake Detectors?
arXiv:2609.10002v1 Announce Type: cross Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibility sha...
Source: arXiv - AI | 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.