Here's your daily roundup of the most relevant AI and ML news for September 12, 2026. Today's digest includes 3 security-focused stories. We're also covering 5 research developments. Click through to read the full articles from our curated sources.
Security & Safety
1. Anthropic Says Seven China-Based AI Labs Ran Industrial-Scale Claude Distillation Attacks
Anthropic on Thursday said it identified and disrupted industrial-scale illicit distillation attacks against Claude from seven labs based in China, including Alibaba, Moonshot, DeepSeek, Z.ai (aka Zhipu), and MiniMax.
Knowledge distillation by itself is a legitimate training method. It refers to...
Source: The Hacker News (Security) | 21 hours ago
2. Claude Used to Automate Exploitation and Data Theft Across Multiple Victims
Anthropic has warned that cybercriminals and state-sponsored hackers alike are using its Claude models for cyber attacks, weapons design, propaganda, and mass surveillance between December 2025 and August 2026.
The threat actors, which the artificial intelligence (AI) company has branded Generat...
Source: The Hacker News (Security) | 23 hours ago
3. Russian State-Sponsored Hackers Use Claude to Rebuild Malware After Detection
Anthropic on Thursday revealed it disrupted a campaign mounted by a Russian state-sponsored threat actor that abused Claude for developing an AI-assisted workflow to get ahead of the detection curve.
The operation has been attributed to a cyber espionage group it calls GTG-20006 (where "GTG" sta...
Source: The Hacker News (Security) | 23 hours ago
Research & Papers
4. 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 - AI | 10 hours ago
5. Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
arXiv:2509.07677v5 Announce Type: replace-cross Abstract: Voice Authentication Systems (VAS) use unique vocal characteristics for verification. They are increasingly integrated into high-security sectors such as banking and healthcare. Despite their improvements using deep learning, they face se...
Source: arXiv - AI | 10 hours ago
6. Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions
arXiv:2609.07675v2 Announce Type: replace-cross Abstract: Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets, and time. We study this interpretation gap in a virtual exchange populated by ten role-co...
Source: arXiv - AI | 10 hours ago
7. SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics
arXiv:2609.11180v1 Announce Type: new Abstract: Large language model (LLM) coding agents constantly decide whether a version satisfies a constraint such as ^1.2.3 or >=2.0,1.2 means >=1.3.0) traps every model on Cargo (near 60%), and although standard PEP 440 prefix matching is universal, on zer...
Source: arXiv - AI | 10 hours ago
8. Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code
arXiv:2609.10762v1 Announce Type: cross Abstract: Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of generated and security-sensitive software. Static analysis is widely adopted as a scalable, reproducible, and inexpensive security gate, but ca...
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.